ZeroWw's picture
Upload folder using huggingface_hub
81fefbe verified
metadata
license: mit
language:
  - en

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 03, 14:36:32