{ "architectures": [ "LlamaForCausalLM" ], "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 4096, "model_type": "mixtral", "num_attention_heads": 32, "num_hidden_layers": 1, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.32.0.dev0", "use_cache": true, "vocab_size": 32000, "bias":false }