license, language, pipeline_tag
| license | language | pipeline_tag | |
|---|---|---|---|
| mit |
|
text-generation |
My own (ZeroWw) quantizations. output and embed tensors quantized to f16. all other tensors quantized to q5_k or q6_k.
Result: both f16.q6 and f16.q5 are smaller than q8_0 standard quantization and they perform as well as the pure f16.
Updated on: Wed Jul 24, 19:15:47