daixuancheng's picture
Upload Qwen2ForCausalLM
d398c52 verified
{
"_name_or_path": "/share/project/zhipengchen/cdx/output/RL/ppo_sample8_critic-warm10-lr2e-6_zero_7b_base_useTokenLoss_clipHigh_KLcoeff0/global_step_60/huggingface_critic",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"classifier_dropout": 0.0,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_dropout": "0",
"hidden_size": 3584,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"intermediate_size": 18944,
"label2id": {
"LABEL_0": 0
},
"max_position_embeddings": 131072,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.49.0",
"use_cache": true,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
}