Edit model card
Wiki C4
W4G64 6.88 11.02
W3G64 7.35 11.72

Revisions available in this repository:

  • main (W4G64, scales learned);
  • nfl_w3g64 (W3G64, scales learned);

Evaluations are provided for models with learned scales.
Check the base gemma-2-9b-FLUTE for lm-eval-harness benchmarks.

Downloads last month
8
Safetensors
Model size
3.13B params
Tensor type
F32
·
FP16
·
I16
·
Inference Examples
Inference API (serverless) is not available, repository is disabled.

Collection including radi-cho/gemma-2-9b-it-FLUTE