Downloads · 30 days
10
11% of all-time downloads
Reprithe/gemma-3-4b-it-unslop-GRPO-v3-heretic
gemma-3-4b-it-unslop-GRPO-v3-heretic is a image-text-to-text model from Reprithe. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as gemma.
Downloads · 30 days
10
11% of all-time downloads
All-time downloads
95
Public
Parameters
4.3B
8.6 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors8.6 GB · 100%
From the Hugging Face model README
| Parameter | Value |
|---|---|
| direction_index | per layer |
| attn.o_proj.max_weight | 1.49 |
| attn.o_proj.max_weight_position | 20.30 |
| attn.o_proj.min_weight | 1.24 |
| attn.o_proj.min_weight_distance | 15.39 |
| mlp.down_proj.max_weight | 0.80 |
| mlp.down_proj.max_weight_position | 20.14 |
| mlp.down_proj.min_weight | 0.80 |
| mlp.down_proj.min_weight_distance | 3.73 |
| Metric | This model | Original model (electroglyph/gemma-3-4b-it-unslop-GRPO-v3) |
|---|---|---|
| KL divergence | 0.92 | 0 (by definition) |
| Refusals | 13/100 | 94/100 |
An unslop finetune of google/gemma-3-4b-it
Next version is here: gemma-3-4b-it-unslop-GSPO
Basically the same as last time plus the minor changes above.
training code: train.py