Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,8 @@ base_model: google/gemma-3-4b-it
|
|
| 9 |
|
| 10 |
An unslop finetune of [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it)
|
| 11 |
|
|
|
|
|
|
|
| 12 |
### Changes from my previous test
|
| 13 |
|
| 14 |
- Temperature during training was at 1.0 this time around, model is a lot less weird
|
|
|
|
| 9 |
|
| 10 |
An unslop finetune of [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it)
|
| 11 |
|
| 12 |
+
Next version is here: [gemma-3-4b-it-unslop-GSPO](https://huggingface.co/electroglyph/gemma-3-4b-it-unslop-GSPO)
|
| 13 |
+
|
| 14 |
### Changes from my previous test
|
| 15 |
|
| 16 |
- Temperature during training was at 1.0 this time around, model is a lot less weird
|