CoolFace
Modelpublic

Anvitha369/Deepseek-Merged-Quantized-Model-7B

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes10downloads
config.json46 linesDownload Raw Back to root
1{2  "_name_or_path": "./temp_merged_model",3  "architectures": [4    "Qwen2ForCausalLM"5  ],6  "attention_dropout": 0.0,7  "bos_token_id": 151643,8  "eos_token_id": 151643,9  "hidden_act": "silu",10  "hidden_size": 3584,11  "initializer_range": 0.02,12  "intermediate_size": 18944,13  "max_position_embeddings": 131072,14  "max_window_layers": 28,15  "model_type": "qwen2",16  "num_attention_heads": 28,17  "num_hidden_layers": 28,18  "num_key_value_heads": 4,19  "quantization_config": {20    "_load_in_4bit": true,21    "_load_in_8bit": false,22    "bnb_4bit_compute_dtype": "float16",23    "bnb_4bit_quant_storage": "uint8",24    "bnb_4bit_quant_type": "nf4",25    "bnb_4bit_use_double_quant": true,26    "llm_int8_enable_fp32_cpu_offload": true,27    "llm_int8_has_fp16_weight": false,28    "llm_int8_skip_modules": null,29    "llm_int8_threshold": 6.0,30    "load_in_4bit": true,31    "load_in_8bit": false,32    "quant_method": "bitsandbytes"33  },34  "rms_norm_eps": 1e-06,35  "rope_scaling": null,36  "rope_theta": 10000,37  "sliding_window": null,38  "tie_word_embeddings": false,39  "torch_dtype": "float16",40  "transformers_version": "4.49.0.dev0",41  "use_cache": true,42  "use_mrope": false,43  "use_sliding_window": false,44  "vocab_size": 15206445}46