| { | |
| "architectures": [ | |
| "MixtralForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 2, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 576, | |
| "initializer_range": 0.041666666666666664, | |
| "intermediate_size": 1536, | |
| "is_llama_config": true, | |
| "max_position_embeddings": 32768, | |
| "mlp_bias": false, | |
| "model_type": "mixtral", | |
| "num_attention_heads": 9, | |
| "num_experts_per_tok": 4, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 3, | |
| "num_local_experts": 32, | |
| "output_router_logits": false, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_interleaved": false, | |
| "rope_scaling": { | |
| "factor": 4.0, | |
| "type": "linear" | |
| }, | |
| "rope_theta": 500000, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "4.57.2", | |
| "unsloth_version": "2025.11.6", | |
| "use_cache": true, | |
| "vocab_size": 49166 | |
| } | |