Downloads · 30 days
6
19% of all-time downloads
nshuster/gemma4-31b-augmental-sft-ep2
gemma4-31b-augmental-sft-ep2 is a machine learning model from nshuster. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.
Full-parameter SFT of google/gemma-4-31B (base) on Heralax/Augmental-Dataset (7,831 rows, visual-novel style multi-character roleplay dialogue).
Downloads · 30 days
6
19% of all-time downloads
All-time downloads
32
Public
Parameters
1.5M
62.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors62.5 GB · 100%
From the Hugging Face model README
Full-parameter SFT of google/gemma-4-31B (base) on Heralax/Augmental-Dataset (7,831 rows, visual-novel style multi-character roleplay dialogue).
This is the end-of-epoch-2 checkpoint (480/720 steps). Sibling repos: epoch 1 (-ep1), epoch 3 (-ep3).
| Checkpoint | eval_loss | eval_ppl |
|---|---|---|
| base (step 0) | 1.753 | 5.77 |
epoch 1 (-ep1) | 1.572 | 4.81 |
| epoch 2 (this repo) | 1.521 | 4.58 |
Trained with a plain-text scenario format (no chat template). Prompt the model exactly like this, then let it continue after the trailing speaker tag:
Scenario: {scenario description}
{Speaker A}: "…"
{Speaker B}: "…"
{target speaker}:
Generation ends with <eos>.
train_on_inputs: false)Gemma derivatives are governed by the Gemma Terms of Use, including the Gemma Prohibited Use Policy.