Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
orca_mini_7B-GPTQ / quantize_config.json
TheBloke's picture
Initial GPTQ model commit
6e7f56e
raw
history blame
135 Bytes
{
"bits": 4,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"sym": true,
"true_sequential": true
}