ai-models/OmniGen2
2
0
Fork 0
mirror of https://www.modelscope.cn/OmniGen2/OmniGen2.git synced 2026-04-02 18:12:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

upload model folder to repo

Browse Source
This commit is contained in:
lxlxlxlxlxlx
2025-06-16 07:50:43 +00:00
parent 43f9976329
commit cd09780d2b
37 changed files with 307054 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.gitattributes vendored
View File

@ -44,4 +44,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text *.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text
processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

65
mllm/config.json Normal file
View File

@ -0,0 +1,65 @@
{
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2048,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 128000,
"max_window_layers": 70,
"model_type": "qwen2_5_vl",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": true,
"torch_dtype": "float32",
"transformers_version": "4.51.3",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"depth": 32,
"fullatt_block_indexes": [
7,
15,
23,
31
],
"hidden_act": "silu",
"hidden_size": 1280,
"in_channels": 3,
"in_chans": 3,
"intermediate_size": 3420,
"model_type": "qwen2_5_vl",
"num_heads": 16,
"out_hidden_size": 2048,
"patch_size": 14,
"spatial_merge_size": 2,
"spatial_patch_size": 14,
"temporal_patch_size": 2,
"tokens_per_second": 2,
"torch_dtype": "float32",
"window_size": 112
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 151936
}

15
mllm/generation_config.json Normal file
View File

@ -0,0 +1,15 @@
{
"_attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001,
"transformers_version": "4.51.3"
}

BIN
mllm/model-00001-of-00004.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
mllm/model-00002-of-00004.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
mllm/model-00003-of-00004.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
mllm/model-00004-of-00004.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

831
mllm/model.safetensors.index.json Normal file
View File

@ -0,0 +1,831 @@
{
"metadata": {
"total_size": 15018491904
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors",
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
}
}

24
model_index.json Normal file
View File

@ -0,0 +1,24 @@
{
"_class_name": "OmniGen2Pipeline",
"_diffusers_version": "0.33.1",
"mllm": [
"transformers",
"Qwen2_5_VLForConditionalGeneration"
],
"processor": [
"transformers",
"Qwen2_5_VLProcessor"
],
"scheduler": [
"scheduling_flow_match_euler_discrete",
"FlowMatchEulerDiscreteScheduler"
],
"transformer": [
"transformer_omnigen2",
"OmniGen2Transformer2DModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

28
processor/added_tokens.json Normal file
View File

@ -0,0 +1,28 @@
{
"</tool_call>": 151658,
"<tool_call>": 151657,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endofimg|>": 151666,
"<|endofmeta|>": 151668,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|img|>": 151665,
"<|meta|>": 151667,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

3
processor/chat_template.json Normal file
View File

@ -0,0 +1,3 @@
{
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
}

151388
processor/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

29
processor/preprocessor_config.json Normal file
View File

@ -0,0 +1,29 @@
{
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}

31
processor/special_tokens_map.json Normal file
View File

@ -0,0 +1,31 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

BIN
processor/tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

241
processor/tokenizer_config.json Normal file
View File

@ -0,0 +1,241 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<|img|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151666": {
"content": "<|endofimg|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151667": {
"content": "<|meta|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151668": {
"content": "<|endofmeta|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"processor_class": "Qwen2_5_VLProcessor",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
processor/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

6
scheduler/scheduler_config.json Normal file
View File

@ -0,0 +1,6 @@
{
"_class_name": "FlowMatchEulerDiscreteScheduler",
"_diffusers_version": "0.33.1",
"dynamic_time_shift": true,
"num_train_timesteps": 1000
}

229
scheduler/scheduling_flow_match_euler_discrete.py Normal file
View File

@ -0,0 +1,229 @@
# Copyright 2024 Stability AI, Katherine Crowson and The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import math
from dataclasses import dataclass
from typing import List, Optional, Tuple, Union
import numpy as np
import torch
from diffusers.configuration_utils import ConfigMixin, register_to_config
from diffusers.utils import BaseOutput, logging
from diffusers.schedulers.scheduling_utils import SchedulerMixin
logger = logging.get_logger(__name__) # pylint: disable=invalid-name
@dataclass
class FlowMatchEulerDiscreteSchedulerOutput(BaseOutput):
"""
Output class for the scheduler's `step` function output.
Args:
prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
denoising loop.
"""
prev_sample: torch.FloatTensor
class FlowMatchEulerDiscreteScheduler(SchedulerMixin, ConfigMixin):
"""
Euler scheduler.
This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
methods the library implements for all schedulers such as loading and saving.
Args:
num_train_timesteps (`int`, defaults to 1000):
The number of diffusion steps to train the model.
timestep_spacing (`str`, defaults to `"linspace"`):
The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
shift (`float`, defaults to 1.0):
The shift value for the timestep schedule.
"""
_compatibles = []
order = 1
@register_to_config
def __init__(
self,
num_train_timesteps: int = 1000,
dynamic_time_shift: bool = False
):
timesteps = torch.linspace(0, 1, num_train_timesteps + 1, dtype=torch.float32)[:-1]
self.timesteps = timesteps
self._step_index = None
self._begin_index = None
@property
def step_index(self):
"""
The index counter for current timestep. It will increase 1 after each scheduler step.
"""
return self._step_index
@property
def begin_index(self):
"""
The index for the first timestep. It should be set from pipeline with `set_begin_index` method.
"""
return self._begin_index
# Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler.set_begin_index
def set_begin_index(self, begin_index: int = 0):
"""
Sets the begin index for the scheduler. This function should be run from pipeline before the inference.
Args:
begin_index (`int`):
The begin index for the scheduler.
"""
self._begin_index = begin_index
def index_for_timestep(self, timestep, schedule_timesteps=None):
if schedule_timesteps is None:
schedule_timesteps = self._timesteps
indices = (schedule_timesteps == timestep).nonzero()
# The sigma index that is taken for the **very** first `step`
# is always the second index (or the last index if there is only 1)
# This way we can ensure we don't accidentally skip a sigma in
# case we start in the middle of the denoising schedule (e.g. for image-to-image)
pos = 1 if len(indices) > 1 else 0
return indices[pos].item()
# def time_shift(self, mu: float, sigma: float, t: torch.Tensor):
# return math.exp(mu) / (math.exp(mu) + (1 / t - 1) ** sigma)
def set_timesteps(
self,
num_inference_steps: int = None,
device: Union[str, torch.device] = None,
timesteps: Optional[List[float]] = None,
num_tokens: Optional[int] = None
):
"""
Sets the discrete timesteps used for the diffusion chain (to be run before inference).
Args:
num_inference_steps (`int`):
The number of diffusion steps used when generating samples with a pre-trained model.
device (`str` or `torch.device`, *optional*):
The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
"""
if timesteps is None:
self.num_inference_steps = num_inference_steps
timesteps = np.linspace(0, 1, num_inference_steps + 1, dtype=np.float32)[:-1]
if self.config.dynamic_time_shift and num_tokens is not None:
m = np.sqrt(num_tokens) / 40 # when input resolution is 320 * 320, m = 1, when input resolution is 1024 * 1024, m = 3.2
timesteps = timesteps / (m - m * timesteps + timesteps)
timesteps = torch.from_numpy(timesteps).to(dtype=torch.float32, device=device)
_timesteps = torch.cat([timesteps, torch.ones(1, device=timesteps.device)])
self.timesteps = timesteps
self._timesteps = _timesteps
self._step_index = None
self._begin_index = None
def _init_step_index(self, timestep):
if self.begin_index is None:
if isinstance(timestep, torch.Tensor):
timestep = timestep.to(self.timesteps.device)
self._step_index = self.index_for_timestep(timestep)
else:
self._step_index = self._begin_index
def step(
self,
model_output: torch.FloatTensor,
timestep: Union[float, torch.FloatTensor],
sample: torch.FloatTensor,
generator: Optional[torch.Generator] = None,
return_dict: bool = True,
) -> Union[FlowMatchEulerDiscreteSchedulerOutput, Tuple]:
"""
Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
process from the learned model outputs (most often the predicted noise).
Args:
model_output (`torch.FloatTensor`):
The direct output from learned diffusion model.
timestep (`float`):
The current discrete timestep in the diffusion chain.
sample (`torch.FloatTensor`):
A current instance of a sample created by the diffusion process.
s_churn (`float`):
s_tmin (`float`):
s_tmax (`float`):
s_noise (`float`, defaults to 1.0):
Scaling factor for noise added to the sample.
generator (`torch.Generator`, *optional*):
A random number generator.
return_dict (`bool`):
Whether or not to return a [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] or
tuple.
Returns:
[`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] or `tuple`:
If return_dict is `True`, [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] is
returned, otherwise a tuple is returned where the first element is the sample tensor.
"""
if (
isinstance(timestep, int)
or isinstance(timestep, torch.IntTensor)
or isinstance(timestep, torch.LongTensor)
):
raise ValueError(
(
"Passing integer indices (e.g. from `enumerate(timesteps)`) as timesteps to"
" `EulerDiscreteScheduler.step()` is not supported. Make sure to pass"
" one of the `scheduler.timesteps` as a timestep."
),
)
if self.step_index is None:
self._init_step_index(timestep)
# Upcast to avoid precision issues when computing prev_sample
sample = sample.to(torch.float32)
t = self._timesteps[self.step_index]
t_next = self._timesteps[self.step_index + 1]
prev_sample = sample + (t_next - t) * model_output
# Cast sample back to model compatible dtype
prev_sample = prev_sample.to(model_output.dtype)
# upon completion increase step index by one
self._step_index += 1
if not return_dict:
return (prev_sample,)
return FlowMatchEulerDiscreteSchedulerOutput(prev_sample=prev_sample)
def __len__(self):
return self.config.num_train_timesteps

65
text_encoder/config.json Normal file
View File

@ -0,0 +1,65 @@
{
"architectures": [
"Qwen2_5_VLModel"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2048,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 128000,
"max_window_layers": 70,
"model_type": "qwen2_5_vl",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": true,
"torch_dtype": "float32",
"transformers_version": "4.51.3",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"depth": 32,
"fullatt_block_indexes": [
7,
15,
23,
31
],
"hidden_act": "silu",
"hidden_size": 1280,
"in_channels": 3,
"in_chans": 3,
"intermediate_size": 3420,
"model_type": "qwen2_5_vl",
"num_heads": 16,
"out_hidden_size": 2048,
"patch_size": 14,
"spatial_merge_size": 2,
"spatial_patch_size": 14,
"temporal_patch_size": 2,
"tokens_per_second": 2,
"torch_dtype": "float32",
"window_size": 112
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 151936
}

BIN
text_encoder/model-00001-of-00003.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
text_encoder/model-00002-of-00003.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
text_encoder/model-00003-of-00003.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

441
text_encoder/model.safetensors.index.json Normal file
View File

@ -0,0 +1,441 @@
{
"metadata": {
"total_size": 12343754752
},
"weight_map": {
"embed_tokens.weight": "model-00001-of-00003.safetensors",
"layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
"layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
"layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
"layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
"layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
"layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
"layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"norm.weight": "model-00003-of-00003.safetensors"
}
}

24
tokenizer/added_tokens.json Normal file
View File

@ -0,0 +1,24 @@
{
"</tool_call>": 151658,
"<tool_call>": 151657,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

151388
tokenizer/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

31
tokenizer/special_tokens_map.json Normal file
View File

@ -0,0 +1,31 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

BIN
tokenizer/tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

208
tokenizer/tokenizer_config.json Normal file
View File

@ -0,0 +1,208 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
tokenizer/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

29
transformer/config.json Normal file
View File

@ -0,0 +1,29 @@
{
"_class_name": "OmniGen2Transformer2DModel",
"_diffusers_version": "0.33.1",
"axes_dim_rope": [
40,
40,
40
],
"axes_lens": [
1024,
1664,
1664
],
"ffn_dim_multiplier": null,
"hidden_size": 2520,
"in_channels": 16,
"multiple_of": 256,
"norm_eps": 1e-05,
"num_attention_heads": 21,
"num_kv_heads": 7,
"num_layers": 32,
"num_refiner_layers": 2,
"out_channels": null,
"patch_size": 2,
"text_feat_dim": 2048,
"timestep_scale": 1000.0,
"use_fused_rms_norm": true,
"use_fused_swiglu": true
}

BIN
transformer/diffusion_pytorch_model-00001-of-00002.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
transformer/diffusion_pytorch_model-00002-of-00002.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

589
transformer/diffusion_pytorch_model.safetensors.index.json Normal file
View File

@ -0,0 +1,589 @@
{
"metadata": {
"total_size": 15868645600
},
"weight_map": {
"context_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"context_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"image_index_embedding": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.10.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.11.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.12.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.13.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.14.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.15.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.16.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.17.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.18.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.18.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.18.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.18.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.19.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.2.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.20.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.20.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.21.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.22.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.23.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.24.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.25.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.26.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.27.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.28.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.29.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.3.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.30.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.30.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.31.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"layers.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.4.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.5.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.6.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.7.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.8.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"layers.9.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"noise_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"norm_out.linear_1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"norm_out.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"norm_out.linear_2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
"norm_out.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
"ref_image_patch_embedder.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_patch_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"ref_image_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"time_caption_embed.caption_embedder.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"time_caption_embed.caption_embedder.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"time_caption_embed.caption_embedder.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"time_caption_embed.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"time_caption_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"time_caption_embed.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"time_caption_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
"x_embedder.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
"x_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
}
}

1309
transformer/transformer_omnigen2.py Normal file
View File

File diff suppressed because it is too large Load Diff

38
vae/config.json Normal file
View File

@ -0,0 +1,38 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.33.1",
"_name_or_path": "/share_2/luoxin/modelscope/hub/models/FLUX.1-dev",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}

BIN
vae/diffusion_pytorch_model.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.