DeepRec-Game / config.json
bwzheng0324's picture
Add initial model
786e2ef
Raw
History Blame Contribute Delete
918 Bytes
{
"_name_or_path": "/mnt/nanjingcephfs/project_wx-rec-alg-bdc-exp/bwzheng/Reasoning+Rec-all/RecR1/results/ckpts/game_0522_r-1_0_1_0.2_0_0_0_10_recall20_top0_100_512_128x8_stage2_100/_actor//checkpoint_step40",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"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,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.46.3",
"use_cache": true,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
}