{ "_name_or_path": "adowu/astral-128k", "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.1, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 128000, "model_type": "mistral", "num_attention_heads": 16, "num_hidden_layers": 16, "num_key_value_heads": 8, "pad_token_id": 2, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.39.3", "use_cache": true, "vocab_size": 32002 }