CoolFace
Modelpublic

ari2002/4bit_model

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes8downloads
config.json43 linesDownload Raw Back to root
1{2  "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 128000,9  "eos_token_id": 128001,10  "hidden_act": "silu",11  "hidden_size": 4096,12  "initializer_range": 0.02,13  "intermediate_size": 14336,14  "max_position_embeddings": 8192,15  "mlp_bias": false,16  "model_type": "llama",17  "num_attention_heads": 32,18  "num_hidden_layers": 32,19  "num_key_value_heads": 8,20  "pretraining_tp": 1,21  "quantization_config": {22    "bnb_4bit_compute_dtype": "float16",23    "bnb_4bit_quant_type": "nf4",24    "bnb_4bit_use_double_quant": true,25    "llm_int8_enable_fp32_cpu_offload": false,26    "llm_int8_has_fp16_weight": false,27    "llm_int8_skip_modules": null,28    "llm_int8_threshold": 6.0,29    "load_in_4bit": true,30    "load_in_8bit": false,31    "quant_method": "bitsandbytes"32  },33  "rms_norm_eps": 1e-05,34  "rope_scaling": null,35  "rope_theta": 500000.0,36  "tie_word_embeddings": false,37  "torch_dtype": "float16",38  "transformers_version": "4.41.2",39  "unsloth_version": "2024.5",40  "use_cache": true,41  "vocab_size": 12825642}43