Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature request] Support for "Falcon" model #1650

Closed
hfassold opened this issue May 30, 2023 · 1 comment
Closed

[Feature request] Support for "Falcon" model #1650

hfassold opened this issue May 30, 2023 · 1 comment
Labels
duplicate This issue or pull request already exists

Comments

@hfassold
Copy link

"Falcon" is a new Large Language Model which seems to be better than Llama.
See https://falconllm.tii.ae/ and
https://iamgeekydude.com/2023/05/28/falcon-llm-the-40-billion-parameters-llm/ and
https://www.marktechpost.com/2023/05/28/technology-innovation-institute-open-sourced-falcon-llms-a-new-ai-model-that-uses-only-75-percent-of-gpt-3s-training-compute-40-percent-of-chinchillas-and-80-percent-of-palm-62b/

Actually, it is the best open-source model currently available according to the authors.

Model (for Huggingface Transformers library) with 40B and 7B parameters is available at :
https://huggingface.co/tiiuae/falcon-40b

Would be great if it would be supported also in llama.cpp.
Note it uses some novel layers (FlashAttention, Multiquery).

@Green-Sky
Copy link
Collaborator

duplicate of #1602

@Green-Sky Green-Sky added the duplicate This issue or pull request already exists label May 30, 2023
@j-f1 j-f1 closed this as not planned Won't fix, can't repro, duplicate, stale May 30, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
duplicate This issue or pull request already exists
Projects
None yet
Development

No branches or pull requests

3 participants