longcot_7B / config.json
dsdsdsdfffff's picture
Upload Qwen2ForCausalLM
89a06ac verified
{
"_name_or_path": "/share/project/zhipengchen/RLHF/deepscaler-main/checkpoints/czp_rlhf/verl_new_grpo-qwen_7b_zero-tbs_128-rbs_128-sample_64-kl_0.0-ep_10000-maxlen_8192-plr_1e6-EL_0.0-temp_1.0-reward_zero/global_step_80/actor/huggingface",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 131072,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.1",
"use_cache": true,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
}