TeenyTinyLlama-460m-Chat-awq / quant_config.json
nicholasKluge's picture
Upload folder using huggingface_hub
1d3d63a verified
raw
history blame
90 Bytes
{
"zero_point": true,
"q_group_size": 128,
"w_bit": 4,
"version": "GEMM"
}