Matthew Andrews

BlueNipples's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

posted an update about 2 months ago

view post

Post

541

I'll never understand why people are merging reasoning models with non-reasoning models. It's worse, every time.

You got to train reasoning on reasoning data, and merge reasoning, with reasoning.

See translation

Reply

posted an update 4 months ago

view post

Post

486

arcee-ai/Virtuoso-Lite is really good. That's all lol.

See translation

🤗

1

1

+

Reply

replied to Undi95's post about 1 year ago

view reply

If this is prompting with special code, forgive my dummy question, how does one turn that into a usable fine tune? Using the layers to mass generate DPO pairs for a detox dataset?