{ "_name_or_path": "mesolitica/malaysian-mistral-7b-32k-instructions-v4", "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "quantization_config": { "backend": "autoawq", "bits": 4, "do_fuse": false, "fuse_max_seq_len": null, "group_size": 128, "modules_to_fuse": null, "quant_method": "awq", "version": "gemm", "zero_point": true }, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.36.2", "use_cache": true, "vocab_size": 32000 }