s
Tom-Neverwinter
AI & ML interests
Making improvements to help the world.
Recent Activity
reacted
to
sergiopaniego's
post
with ๐
6 days ago
NEW: @EssentialAI just released Rnj-1, their first 8B model.
You can easily fine-tune it with GRPO using TRL to add reasoning capabilities to a compact mode
Free Colab link: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_rnj_1_instruct.ipynb
More free TRL notebooks: https://huggingface.co/docs/trl/main/en/example_overview#notebooks
new activity
10 days ago
microsoft/VibeVoice-Realtime-0.5B:Safety or the joke there in
Organizations
None yet