Gemma3NPC-it-beta
Collection
A new attempt at training Gemma3NPC, with less conservative training parameters
•
3 items
•
Updated
Gemma3NPC-it-beta
A test model with less convervative training parameters
The Q8_0 quantized version of Gemma3NPC-it-beta-Float16.
As mentioned in our original article, we employed a very conservative training parameters for Gemma3NPC
Ever since then, we have always wanted to test the performance of the model when we make the training parameters less conservative.
So we present Gemma3NPC-it-beta.
Check out our training notebook here
Training parameters compared to Gemma3NPC-it
| Parameter | Gemma3NPC-it | Gemma3NPC-it-beta |
|---|---|---|
| Learning Rate | 2e-5 | 2.5e-5 (+25%) |
| Warmup Steps | 800 | 100 |
| gradient clipping | 0.4 | 1.0 |
Here is a graph of the Step Training Loss, saved every 10 steps:
- Downloads last month
- 4
Hardware compatibility
Log In
to add your hardware
8-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for chimbiwide/Gemma3NPC-it-beta-Q8-GGUF
Base model
chimbiwide/Gemma3NPC-it-beta-float16