Files
Meta-Llama-3-8B-Instruct-GP…/quantize_config.json

11 lines
223 B
JSON
Raw Permalink Normal View History

{
"bits": 4,
"dataset": "sharegpt-gpt4-mini",
"group_size": 128,
"damp_percent": 0.1,
"desc_act": false,
"sym": true,
"true_sequential": true,
"quant_method": "gptq",
"modules_in_block_to_quantize": null
}