| { | |
| "_name_or_path": "/dataset/industry_gpt/llm_infer/MetaMath/output/qwen2-57b-distill-data-374k-bs32-lr5e-6-linear-fix-sample0.8-sharded", | |
| "architectures": [ | |
| "Qwen2MoeForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "decoder_sparse_step": 1, | |
| "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_moe", | |
| "moe_intermediate_size": 2560, | |
| "norm_topk_prob": false, | |
| "num_attention_heads": 28, | |
| "num_experts": 64, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "output_router_logits": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "factor": 2.0, | |
| "original_max_position_embeddings": 32768, | |
| "type": "yarn" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "router_aux_loss_coef": 0.001, | |
| "shared_expert_intermediate_size": 20480, | |
| "sliding_window": 131072, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |