Non- Math Use Cases?

#18
by DeFactOfficial - opened

How does this model perform at tasks such as tool use, RAG, general purpose QA? Has it been benchmarked for tasks other than math? Is SFT likely to be successful for these sorts of tasks? Sorry if this is a naive question, I'm new to training models - usually I just inference them, but this model seems like something really special so I'm ready to learn whatever I need

Agentica org

We are going to release models for other use cases. Stay tuned!

We are going to release models for other use cases. Stay tuned!

Coding perhaps? ( python mainly ). Testing last night, it struggled a bit getting some simple code right. But i know im an edge-case.

Sign up or log in to comment