32 lines
862 B
JSON
32 lines
862 B
JSON
{
|
|
"_name_or_path": "/scratch/group/optmai/gli/dro_rl/checkpoints/delta_scaler/pgD1e4-droT10-b32-lr2e6-B0/actor/best_global_step_940",
|
|
"architectures": [
|
|
"Qwen2ForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151646,
|
|
"eos_token_id": 151643,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 1536,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 8960,
|
|
"max_position_embeddings": 131072,
|
|
"max_window_layers": 21,
|
|
"model_type": "qwen2",
|
|
"num_attention_heads": 12,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 2,
|
|
"pad_token_id": 151643,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.47.1",
|
|
"use_cache": true,
|
|
"use_mrope": false,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151936
|
|
}
|