18 lines
339 B
Markdown
18 lines
339 B
Markdown
|
|
---
|
|
license: mit
|
|
language:
|
|
- en
|
|
pipeline_tag: 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: Fri Oct 25, 14:14:40
|