J1_7B_RL / config.json
test-time-scaling's picture
Upload J1-7B model trained with RL
3455b0d verified
{
"_name_or_path": "/aifs4su/hansirui_2nd/zhanqimin/verl/checkpoints/lmj_r1_verl/reinforce/rise_no_chinese/on_sft_qwen2.5_7b_modify_template_prompt_template_2_rewardbench_8192_3epoch_apply_chat_template_0322T01:52/global_step_300/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": "4.49.0",
"use_cache": false,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
}