Downloads · 30 days
0
gemma4-26b-a4b-gsm8k-sft-step233-human-reference-maxtext
dureduck/gemma4-26b-a4b-gsm8k-sft-step233-human-reference-maxtext
gemma4-26b-a4b-gsm8k-sft-step233-human-reference-maxtext is a machine learning model from dureduck. 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 maxtext.
Params-only MaxText/Orbax checkpoint converted from dureduck/gemma-4-26b-a4b-gsm8k-sft-step233 (revision 186f7e33). Published so evaluations can run in any region without copying buckets across regions. Layout: checkp…
Access
Public
Updated Sep 23, 2026
Repo size
39.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other39.4 GB · 100%
At a glance
- Library
- maxtext
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- 5c820574
Base models
Datasets
Model card
From the Hugging Face model README
Gemma 4 26B-A4B GSM8K SFT (human reference solutions), step 233, MaxText params
Params-only MaxText/Orbax checkpoint converted from dureduck/gemma-4-26b-a4b-gsm8k-sft-step233 (revision 186f7e33). Published so evaluations can run in any region without copying buckets across regions. Layout: checkpoints/233/model_params/, tag checkpoint-233, publication-manifest.json records source object generations and payload hashes. No optimizer state, no credentials, no source data.
- Library
- maxtext
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026