GemmaReLe

A test model for ReLe

image

(btw, we sort of did)


The Gemma3NPC series were meant to be a sort of general purposed video game RP model.

This time, using the chimbiwide/ReLe_Synthetic_v1_json, we trained a model to specifically act as ReLe.

For more information on Who is ReLe?, visit the dataset README.

Warning: This is NOT a general purpose model. Performance requires further testing.

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

Graph of the Step Training Loss, saved every 10 steps:

chart


Fun Discovery

For the first time ever, we encountered a whole number trianing loss.

image

Downloads last month
55
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for chimbiwide/GemmaReLe-float16

Quantizations
2 models

Dataset used to train chimbiwide/GemmaReLe-float16

Collection including chimbiwide/GemmaReLe-float16