| { | |
| "_name_or_path": "/apdcephfs_qy3/share_301372554/share_info/qianggao/llama3/output/05-17_llama3-8x8b-Instruct_sft_firefly_dolphin_float32___bs__maxlen_1024_pad_right_lr_2e-5_format_llama3-8x8b-Instruct/checkpoint-200", | |
| "architectures": [ | |
| "LlamaMoEForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128001, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_local_experts": 8, | |
| "output_router_logits": true, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "router_aux_loss_coef": 0.02, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.0", | |
| "use_cache": false, | |
| "vocab_size": 128256 | |
| } | |