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 Aug 21, 13:35:36
- Downloads last month
- 218
Inference API (serverless) is not available, repository is disabled.