mirror of
https://www.modelscope.cn/Qwen/QwQ-32B.git
synced 2025-12-08 21:34:21 +08:00
30 lines
920 B
JSON
30 lines
920 B
JSON
{
|
|
"_name_or_path": "/cpfs01/data/shared/Group-m6/chuanyi.yl/ckpts/sft/dense/hf-ckpts/32b.stage2--cptv9-base100w-cpt32k-0218_Ma_Co_STE_Rea_Age_Gen_dgb-32B.qwen2.5B-bf16-mp8-pp1-lr-7e-6-minlr-7e-7-bs-128-gpus-128-seqlen-32768-step8392",
|
|
"architectures": [
|
|
"Qwen2ForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151643,
|
|
"eos_token_id": 151645,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 5120,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 27648,
|
|
"max_position_embeddings": 65536,
|
|
"max_window_layers": 64,
|
|
"model_type": "qwen2",
|
|
"num_attention_heads": 40,
|
|
"num_hidden_layers": 64,
|
|
"num_key_value_heads": 8,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000.0,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.45.2",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 152064
|
|
}
|