mirror of
https://www.modelscope.cn/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B.git
synced 2026-04-02 21:52:53 +08:00
35 lines
859 B
JSON
35 lines
859 B
JSON
{
|
|
"architectures": [
|
|
"Qwen3ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151643,
|
|
"eos_token_id": 151645,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 12288,
|
|
"max_position_embeddings": 131072,
|
|
"max_window_layers": 36,
|
|
"model_type": "qwen3",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 36,
|
|
"num_key_value_heads": 8,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": {
|
|
"rope_type": "yarn",
|
|
"factor": 4.0,
|
|
"original_max_position_embeddings": 32768,
|
|
"attn_factor": 0.8782488562869419
|
|
},
|
|
"rope_theta": 1000000,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.51.0",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151936
|
|
} |