[kiraaa]

the paper does not live up to the quality of model lol

[bee_rider]

Maybe these models should start writing themselves up.

Provide the model with an outline of a 20-or-so page research paper about itself and have it fill in the blanks. The researchers might have to provide textual description of the figures in the “experiments” section.

[ramesh31]

Is it better than llama 2?

[tarruda]

It is better than llama 2 7b and 13b. I tried the OpenOrca fine tune and it is very good, even when 4-bit quantized

[faizshah]

What does OpenOrca do? It’s just instruction tuning it?

[tarruda]

Yes, it is a instruction tune dataset: https://huggingface.co/datasets/Open-Orca/OpenOrca

It felt different from the official Mistral7B-Instruct. One of the highlights with the OpenOrca version is that you can steer the model with a system prompt (eg "You are a 5 year old")

[sebzim4500]

For its size, yes. In absolute terms it is obviously less capable than llama-2-70B

[espadrine]

For now. Huggingface[0] mentioned a DPO-fine-tuned version, Zephyr 7B, which it claims is competitive with Llama2-70B[1].

[0]: https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat

[1]: https://twitter.com/huggingface/status/1711780979574976661

[brucethemoose2]

Oh, they uploaded the weights. I missed this one, cheers!

[andai]

I found llama-2-70B to be a bit worse than GPT-4. (So, pretty good!) But I did not compare with GPT-3.

How do llama-2-70B and Mistral 7B compare with GPT-3?

[TheRoque]

Yes