densenet

Gemma-4-31B-StyleTune-heretic-ara

README

License: apache-2.0

Table with columns: Parameter, Value
Parameter	Value
start_layer_index	30
end_layer_index	48
preserve_good_behavior_weight	0.8437
steer_bad_behavior_weight	0.0025
overcorrect_relative_weight	0.9644
neighbor_count	15

Table with columns: Metric, This model, Original model (Gryphe/Gemma-4-31B-StyleTune)
Metric	This model	Original model (Gryphe/Gemma-4-31B-StyleTune)
KL divergence	0.0733	0 (by definition)
Refusals	8/100	99/100

This gemma4 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Container

Run this model inference with full control and performance in your environment.

Model Details

Model Provider

densenet

Model Tree

Base

Gryphe/Gemma-4-31B-StyleTune

Fine-tuned

this model

Input Modalities

TextImage

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

License: apache-2.0

Table with columns: Parameter, Value
Parameter	Value
start_layer_index	30
end_layer_index	48
preserve_good_behavior_weight	0.8437
steer_bad_behavior_weight	0.0025
overcorrect_relative_weight	0.9644
neighbor_count	15

Table with columns: Metric, This model, Original model (Gryphe/Gemma-4-31B-StyleTune)
Metric	This model	Original model (Gryphe/Gemma-4-31B-StyleTune)
KL divergence	0.0733	0 (by definition)
Refusals	8/100	99/100

This gemma4 model was trained 2x faster with Unsloth and Huggingface's TRL library.