Alignment-Lab-AI/Mistral-Large-Instruct-2407-bnb-4bit
016
1{2 "_name_or_path": "unsloth/Mistral-Large-Instruct-2407",3 "architectures": [4 "MistralForCausalLM"5 ],6 "attention_dropout": 0.0,7 "bos_token_id": 1,8 "eos_token_id": 2,9 "head_dim": 128,10 "hidden_act": "silu",11 "hidden_size": 12288,12 "initializer_range": 0.02,13 "intermediate_size": 28672,14 "max_position_embeddings": 131072,15 "model_type": "mistral",16 "num_attention_heads": 96,17 "num_hidden_layers": 88,18 "num_key_value_heads": 8,19 "pad_token_id": 750,20 "quantization_config": {21 "_load_in_4bit": true,22 "_load_in_8bit": false,23 "bnb_4bit_compute_dtype": "bfloat16",24 "bnb_4bit_quant_storage": "uint8",25 "bnb_4bit_quant_type": "nf4",26 "bnb_4bit_use_double_quant": true,27 "llm_int8_enable_fp32_cpu_offload": false,28 "llm_int8_has_fp16_weight": false,29 "llm_int8_skip_modules": null,30 "llm_int8_threshold": 6.0,31 "load_in_4bit": true,32 "load_in_8bit": false,33 "quant_method": "bitsandbytes"34 },35 "rms_norm_eps": 1e-05,36 "rope_theta": 1000000.0,37 "sliding_window": null,38 "tie_word_embeddings": false,39 "torch_dtype": "bfloat16",40 "transformers_version": "4.44.0",41 "unsloth_version": "2024.8",42 "use_cache": true,43 "vocab_size": 3276844}45 