| { | |
| "_name_or_path": "/mnt/petrelfs/quxiaoye/models/sft-v2/moe8top2_onestage", | |
| "add_rescale_bias": false, | |
| "architectures": [ | |
| "MixtralForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_experts": null, | |
| "auto_map": { | |
| "AutoConfig": "configuration_mixtral.MixtralConfig", | |
| "AutoModel": "modeling_mixtral.MixtralModel", | |
| "AutoModelForCausalLM": "modeling_mixtral.MixtralForCausalLM" | |
| }, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128009, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1792, | |
| "intermediate_size_residual": null, | |
| "max_position_embeddings": 8192, | |
| "model_type": "mixtral", | |
| "moe_type": "modulelist", | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_local_experts": 8, | |
| "num_moe_contract_layers": 0, | |
| "output_router_logits": true, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "router_aux_loss_coef": 0.01, | |
| "scale_factor": 4.0, | |
| "scale_factor_attn": null, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "top_k_attn": null, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.42.4", | |
| "use_attn_moe": false, | |
| "use_cache": false, | |
| "use_layer_wise_balance": false, | |
| "vocab_size": 128256 | |
| } | |