Downloads · 30 days
0
latkes/rankalign-v7-gemma-4-31B-it-d2.14-e0-humaneval-v2.1correct-upper-all-p0-nv1-ng1-cft-lo0.1-fix1
rankalign-v7-gemma-4-31B-it-d2.14-e0-humaneval-v2.1correct-upper-all-p0-nv1-ng1-cft-lo0.1-fix1 is a machine learning model from latkes. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
Fine-tuned checkpoint from the rankalign project.
Downloads · 30 days
0
Access
Public
Updated May 25, 2026
Repo size
490 MB
Likes
0
Public
Click a slice to open those files.
.safetensors490 MB · 100%
From the Hugging Face model README
Fine-tuned checkpoint from the rankalign project.
| Field | Value |
|---|---|
| Base model | google/gemma-4-31B-it |
| Version | v7 |
| Task | humaneval-v2.1correct-upper-all |
| Epoch | 0 |
| Delta | 2.14 |
| Typicality correction | none |
| Length normalization | False |
| Preference loss weight | 0 |
| NLL validator weight | 1 |
| NLL generator weight | 1 |
| Validator log-odds | False |
| Force same-x | False |
| Semi-supervised ratio | None |
| Labeled-only ratio | 0.1 |
Original checkpoint name: v7-google--gemma-4-31B-it-delta2.14-epoch0--humaneval-v2.1correct-upper-all--d2g--random--alpha1.0--full-completion--pref0.0--nllv1.0--nllg1.0--cft--labelonly0.1--fix1
To evaluate:
python scripts/eval_by_claude.py \
--model TAUR-dev/rankalign-v7-gemma-4-31B-it-d2.14-e0-humaneval-v2.1correct-upper-all-p0-nv1-ng1-cft-lo0.1-fix1 \
--task humaneval-v2.1correct-upper-all \
--split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
--self-typicality