mirror of
https://www.modelscope.cn/black-forest-labs/FLUX.1-dev.git
synced 2026-04-02 16:22:53 +08:00
- Add diffusers format weights (5d4717a3dc82fa40a286f48bb71f1ead5c517800) - update readme with diffusers goodies (97a16425ff5c88f218d76851f32820e703ea813d) - Update README.md (9ae394376d269f108989e648378f3ee54cfe7d7b) - Upload folder using huggingface_hub (f2a94b28d7167624c443a40aaa0334351bd62c02) - update scheduler (fe1bfe0b434c9a621a4d4ddad4f57204dcf55d23) Co-authored-by: Dhruv Nair <dn6@users.noreply.huggingface.co> Co-authored-by: Apolinário from multimodal AI art <multimodalart@users.noreply.huggingface.co>
33 lines
782 B
JSON
33 lines
782 B
JSON
{
|
|
"_name_or_path": "google/t5-v1_1-xxl",
|
|
"architectures": [
|
|
"T5EncoderModel"
|
|
],
|
|
"classifier_dropout": 0.0,
|
|
"d_ff": 10240,
|
|
"d_kv": 64,
|
|
"d_model": 4096,
|
|
"decoder_start_token_id": 0,
|
|
"dense_act_fn": "gelu_new",
|
|
"dropout_rate": 0.1,
|
|
"eos_token_id": 1,
|
|
"feed_forward_proj": "gated-gelu",
|
|
"initializer_factor": 1.0,
|
|
"is_encoder_decoder": true,
|
|
"is_gated_act": true,
|
|
"layer_norm_epsilon": 1e-06,
|
|
"model_type": "t5",
|
|
"num_decoder_layers": 24,
|
|
"num_heads": 64,
|
|
"num_layers": 24,
|
|
"output_past": true,
|
|
"pad_token_id": 0,
|
|
"relative_attention_max_distance": 128,
|
|
"relative_attention_num_buckets": 32,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.43.3",
|
|
"use_cache": true,
|
|
"vocab_size": 32128
|
|
}
|