Update SuperNova-Medius with a merge with Qwen/Qwen2.5-Coder-14B-Instruct + Further Training ๐Ÿ˜‹

#12
by Joseph717171 - opened

Qwen just dropped their 14B coder instruct model. Arcee-AI, it would be amazing if you merged SuperNova-Medius with Qwen/Qwen2.5-Coder-14B-Instruct and further trained it. ๐Ÿ˜‹

Am, I dreaming, or is this viable? Qwen/Qwen2.5-Coder-14B-Instruct >= GPT4 at coding. ๐Ÿ˜‹

@Crystalcareai @chargoddard

Arcee AI org

Not a bad idea. We have quite a few models in the works right now, but I'll make sure this gets on our radar.

There's a need for a better-trained coder model! Fill-in-the-middle is especially important. Is it just me, or does nothing so far do autocomplete on local Continue.dev as well as Deepseek V2 Lite? I'd like to see that change.

@Crystalcareai Thanks! Your guys' models are helping me with my University studies. It's amazing how much smarter SMOL LLMs become when you use the logits from a Large Foundation Model to distill knowledge and capabilities into them. I can't wait for what you guys are cooking SMOL-wise. Is it possible to get a list of base models, which are being used, please? ๐Ÿ™

Arcee AI org

Qwen just dropped their 14B coder instruct model. Arcee-AI, it would be amazing if you merged SuperNova-Medius with Qwen/Qwen2.5-Coder-14B-Instruct and further trained it. ๐Ÿ˜‹

Am, I dreaming, or is this viable? Qwen/Qwen2.5-Coder-14B-Instruct >= GPT4 at coding. ๐Ÿ˜‹

@Crystalcareai @chargoddard

you are not dreaming! ๐Ÿ˜‹
https://huggingface.co/arcee-ai/SuperNova-Medius/discussions/4#6717ebeb276e0b54768d19c8

Hey, this is such an interesting idea. Do we have any update when this will come under processing? @MaziyarPanahi @Crystalcareai
Thanks

Arcee AI org

Weโ€™re currently training around 10 different modelsโ€”not to mention the ~15 our Customer Success team is working on for clientsโ€”so there are about 25 models in progress across Arcee right now. Some are aimed for public release, while others are part of closed-source offerings slated to be available around December 2nd. A strong 14B coder model is definitely in development, though the release date is still to be determined. Weโ€™re firing on all cylinders and will have some exciting updates to share soon!

Arcee AI org

And some of those updates wonโ€™t be just models! ๐Ÿ˜‰

Iโ€™m excited! ๐Ÿคฉ By the way, does Arcee-AI have a discord all of us fans/enthusiasts could join? Huggingface is great, but the flow of information is not as optimal as it could be. If you guys have a discord, please link it. I would be most appreciative of it. ๐Ÿ˜‹

Arcee AI org

we've thought about doing a mergekit discord - but we don't have anything at this moment. I'll renew the discussions!

Sign up or log in to comment