Text Generation
Transformers
Safetensors
5 languages
RefinedWeb
falcon-40b
long-context
falcon
NTK-YaRN
custom_code
text-generation-inference
4-bit precision
alfred-40B-1023-AWQ / quant_config.json
TheBloke's picture
AWQ model commit
a99ad1e
{
"zero_point": true,
"q_group_size": 128,
"w_bit": 4,
"version": "GEMM"
}