| { |
| "_name_or_path": "./hydra", |
| "architectures": [ |
| "MixtralForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "hidden_act": "silu", |
| "hidden_size": 7168, |
| "initializer_range": 0.02, |
| "intermediate_size": 20480, |
| "max_position_embeddings": 200000, |
| "model_type": "mixtral", |
| "num_attention_heads": 56, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 60, |
| "num_key_value_heads": 8, |
| "num_local_experts": 4, |
| "output_router_logits": false, |
| "pad_token_id": 0, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 5000000.0, |
| "router_aux_loss_coef": 0.001, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.37.2", |
| "use_cache": true, |
| "vocab_size": 64000 |
| } |
|
|