{ "_name_or_path": "ahxt/LiteLlama-460M-1T", "architectures": [ "MixtralForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layernorm_epsilon": 1e-05, "max_position_embeddings": 1024, "model_type": "mixtral", "num_attention_heads": 16, "num_experts_per_tok": 2, "num_hidden_layers": 24, "num_key_value_heads": 2, "num_local_experts": 512, "output_router_logits": false, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.37.0.dev0", "use_cache": true, "vocab_size": 50304 }