{ | |
"_name_or_path": "/workspace/R1/deepscaler/checkpoints/t1-3b/t1-3b-grpo-16k/actor/global_step_460", | |
"architectures": [ | |
"Qwen2ForCausalLM" | |
], | |
"attention_dropout": 0.0, | |
"eos_token_id": 151645, | |
"hidden_act": "silu", | |
"hidden_size": 2048, | |
"initializer_range": 0.02, | |
"intermediate_size": 11008, | |
"max_position_embeddings": 32768, | |
"max_window_layers": 70, | |
"model_type": "qwen2", | |
"num_attention_heads": 16, | |
"num_hidden_layers": 36, | |
"num_key_value_heads": 2, | |
"pad_token_id": 151643, | |
"rms_norm_eps": 1e-06, | |
"rope_scaling": { | |
"factor": 1.0, | |
"rope_type": "linear", | |
"type": "linear" | |
}, | |
"rope_theta": 1000000.0, | |
"sliding_window": null, | |
"tie_word_embeddings": true, | |
"torch_dtype": "float32", | |
"transformers_version": "4.47.1", | |
"use_cache": true, | |
"use_sliding_window": false, | |
"vocab_size": 151936 | |
} | |