Shallow342/4bitmodel2
08
1{2 "_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",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": 4096,12 "initializer_range": 0.02,13 "intermediate_size": 14336,14 "max_position_embeddings": 32768,15 "model_type": "mistral",16 "num_attention_heads": 32,17 "num_hidden_layers": 32,18 "num_key_value_heads": 8,19 "pad_token_id": 770,20 "quantization_config": {21 "bnb_4bit_compute_dtype": "float16",22 "bnb_4bit_quant_type": "nf4",23 "bnb_4bit_use_double_quant": true,24 "llm_int8_enable_fp32_cpu_offload": false,25 "llm_int8_has_fp16_weight": false,26 "llm_int8_skip_modules": null,27 "llm_int8_threshold": 6.0,28 "load_in_4bit": true,29 "load_in_8bit": false,30 "quant_method": "bitsandbytes"31 },32 "rms_norm_eps": 1e-05,33 "rope_scaling": null,34 "rope_theta": 1000000.0,35 "sliding_window": null,36 "tie_word_embeddings": false,37 "torch_dtype": "float16",38 "transformers_version": "4.44.2",39 "unsloth_version": "2024.9.post4",40 "use_cache": true,41 "vocab_size": 3276842}43 