tensorfiend

tunelm-gemma4-4b-grpo-pilot-20260928-60-final

README

License: apache-2.0

tensorfiend/tunelm-gemma4-4b-grpo-pilot-20260928-60-final

TuneLM merged checkpoint derived from tensorfiend/tunelm-gemma4-4b-sft-quality-20260927-86-best. The weights were modified by fine-tuning for Strudel generation.

Run name: gemma4-4b-grpo-pilot
Training step: 60
Checkpoint tag: final
Best eval loss: -0.018107524141669273

See LICENSE and NOTICE for the base-model license and modification notice.

Available on FriendliAI

Dedicated Endpoints

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

Learn more

Model Details

Model Provider

tensorfiend

Model Tree

Base

tensorfiend/tunelm-gemma4-4b-sft-quality-20260927-86-best

Fine-tuned

this model

Input Modalities

TextImage

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer