Text Generation
Transformers
Safetensors
English
llama
text generation
instruct
text-generation-inference
4-bit precision
Pygmalion-2-7B-AWQ / quant_config.json
TheBloke's picture
AWQ model commit
485ccce
{
"zero_point": true,
"q_group_size": 128,
"w_bit": 4,
"version": "GEMM"
}