| { |
| "_name_or_path": "Locutusque/TinyMistral-248M", |
| "architectures": [ |
| "MixtralForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "hidden_act": "silu", |
| "hidden_size": 64, |
| "initializer_range": 0.02, |
| "intermediate_size": 256, |
| "max_position_embeddings": 32768, |
| "model_type": "mixtral", |
| "num_attention_heads": 32, |
| "num_experts_per_tok": 4, |
| "num_hidden_layers": 12, |
| "num_key_value_heads": 8, |
| "num_local_experts": 4, |
| "output_router_logits": false, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 10000.0, |
| "router_aux_loss_coef": 0.001, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.37.1", |
| "use_cache": true, |
| "vocab_size": 32005 |
| } |
|
|