quantized_ontologyhermes_4bits / quantize_config.json
pranavsid's picture
Upload quantized model files
f71876d verified
raw
history blame contribute delete
214 Bytes
{
"bits": 4,
"dataset": "wikitext2",
"group_size": 128,
"damp_percent": 0.1,
"desc_act": false,
"sym": true,
"true_sequential": true,
"quant_method": "gptq",
"modules_in_block_to_quantize": null
}