josephmayo
Gemma-4-E4B-Forge-SLM
Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
Proof
- Benchmark: 50 HumanEval + 50 MBPP tasks
- Before greedy: 29/100
- Before sample: 45/100
- Before repair: 48/100
- Final label: after_sft
- Final greedy: 44/100
- Final sample: 49/100
- Final repair: 49/100
- Release gate: True
Artifacts included in the Kaggle proof output: release_summary.json, eval_before_after_full_code.csv, and trainer logs.
Model provider
josephmayo
Model tree
Base
google/gemma-4-E4B-it
Adapter
this model
Modalities
Input
Text, Image
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information