| { | |
| "_name_or_path": "/home/fit/huangg/WORK/zqc/reason_rl/checkpoints/code_io/code_io/code_io_full_v0_coder14b/test_answer/Qwen2.5-Coder-14B/answer_conditional/global_step_300/actor/huggingface", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "eos_token_id": 151643, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 48, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 8, | |
| "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": "4.47.1", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064, | |
| "quantization_config": { | |
| "quant_method": "exl3", | |
| "version": "0.0.2", | |
| "bits": 5.0, | |
| "head_bits": 6, | |
| "calibration": { | |
| "rows": 100, | |
| "cols": 2048 | |
| }, | |
| "out_scales": "auto" | |
| } | |
| } |