| { | |
| "_name_or_path": "AI-MO/NuminaMath-7B-TIR", | |
| "architectures": [ | |
| "MixtralForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 100000, | |
| "eos_token_id": 100001, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "mlp_bias": false, | |
| "model_type": "mixtral", | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 32, | |
| "num_local_experts": 2, | |
| "output_router_logits": false, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.44.2", | |
| "use_cache": true, | |
| "vocab_size": 102400 | |
| } | |