LUFFY-Qwen-Instruct-7B / config.json
Elliott's picture
Upload Qwen2ForCausalLM
60e503b verified
{
"_name_or_path": "/mnt/petrelfs/yanjianhao/RL/rl4kd-ds/deepscaler/verl/checkpoints/baseline-rl-exps/INSTRUCT-7B_17_DRGRPO_v9_8K_P_DIV_P_0.1_NOCLIP/best-before-500/actor/",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"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": "float32",
"transformers_version": "4.46.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}