Quantization
Collection
A collection of quantized models. All the models can be fine-tuned by adding a LoRA Adapter.
•
84 items
•
Updated
•
3
Original Base Model: google/gemma-2-27b-it
.
Link: https://huggingface.co./google/gemma-2-27b-it
"quantization_config": {
"bits": 4,
"checkpoint_format": "gptq",
"damp_percent": 0.1,
"desc_act": true,
"group_size": 128,
"model_file_base_name": null,
"model_name_or_path": null,
"quant_method": "gptq",
"static_groups": false,
"sym": true,
"true_sequential": true
},
Source Codes: https://github.com/vkola-lab/medpodgpt/tree/main/quantization.