jsbai-aaron commited on
Commit
3367526
·
verified ·
1 Parent(s): 45156bc

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -47,6 +47,8 @@ The NVFP4 quantization preserves instruction-following (within ~1 point of BF16)
47
 
48
  *12/32 on a 32-instance subset (the same slice our comparisons use). The quantization costs roughly half the generalization capability of the BF16.
49
 
 
 
50
  Our decontamination protocol is published with the model: none of these benchmark problems overlap the training data.
51
 
52
  ## What it does
 
47
 
48
  *12/32 on a 32-instance subset (the same slice our comparisons use). The quantization costs roughly half the generalization capability of the BF16.
49
 
50
+ Note: Terminal-Bench 2.1 and future benchmark additions are evaluated on the BF16 release (Aztec-Coder-4B). Community quants are welcome; see the BF16 model card for full benchmark coverage.
51
+
52
  Our decontamination protocol is published with the model: none of these benchmark problems overlap the training data.
53
 
54
  ## What it does