| { | |
| "architectures": [ | |
| "MixtralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attn_implementation": "flash_attention_2", | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3584, | |
| "max_position_embeddings": 1024, | |
| "model_type": "mixtral", | |
| "num_attention_heads": 8, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 2, | |
| "num_local_experts": 2, | |
| "output_router_logits": true, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "router_aux_loss_coef": 0.02, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.38.2", | |
| "use_cache": false, | |
| "vocab_size": 32000 | |
| } | |