CoolFace
Modelpublic

DominusDeorum/Knowledge-rep_mlp-model

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes10downloads
config.json55 linesDownload Raw Back to root
1{2  "_name_or_path": "unsloth/Llama-3.2-1B-Instruct-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": [10    128001,11    128008,12    12800913  ],14  "head_dim": 64,15  "hidden_act": "silu",16  "hidden_size": 2048,17  "initializer_range": 0.02,18  "intermediate_size": 8192,19  "max_position_embeddings": 131072,20  "mlp_bias": false,21  "model_type": "llama",22  "num_attention_heads": 32,23  "num_hidden_layers": 16,24  "num_key_value_heads": 8,25  "pad_token_id": 128004,26  "pretraining_tp": 1,27  "quantization_config": {28    "bnb_4bit_compute_dtype": "float16",29    "bnb_4bit_quant_type": "nf4",30    "bnb_4bit_use_double_quant": true,31    "llm_int8_enable_fp32_cpu_offload": false,32    "llm_int8_has_fp16_weight": false,33    "llm_int8_skip_modules": null,34    "llm_int8_threshold": 6.0,35    "load_in_4bit": true,36    "load_in_8bit": false,37    "quant_method": "bitsandbytes"38  },39  "rms_norm_eps": 1e-05,40  "rope_scaling": {41    "factor": 32.0,42    "high_freq_factor": 4.0,43    "low_freq_factor": 1.0,44    "original_max_position_embeddings": 8192,45    "rope_type": "llama3"46  },47  "rope_theta": 500000.0,48  "tie_word_embeddings": true,49  "torch_dtype": "float16",50  "transformers_version": "4.46.2",51  "unsloth_version": "2024.11.7",52  "use_cache": true,53  "vocab_size": 12825654}55