{ "_name_or_path": "./largestral", "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 12288, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 131072, "model_type": "mistral", "num_attention_heads": 96, "num_hidden_layers": 72, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.46.3", "use_cache": true, "vocab_size": 32768, "quantization_config": { "quant_method": "exl2", "version": "0.2.3", "bits": 2.25, "head_bits": 6, "calibration": { "rows": 115, "length": 2048, "dataset": "(default)" } } }