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.

Sign up for GitHub

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

Jump to bottom

Update supported models list #360

Merged
merged 3 commits into from
Dec 21, 2023
Merged

Update supported models list #360

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b0e5a99
update supported models
mrwyattii Dec 21, 2023
5508653
update model count
mrwyattii Dec 21, 2023
1517931
fix wrong url
mrwyattii Dec 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,14 +78,16 @@ Under-the-hood MII is powered by [DeepSpeed-Inference](https://github.com/micros

# Supported Models

MII currently supports over 13,000 models across three popular model architectures. We plan to add additional models in the near term, if there are specific model architectures you would like supported please [file an issue](https://github.com/microsoft/DeepSpeed-MII/issues) and let us know. All current models leverage Hugging Face in our backend to provide both the model weights and the model's corresponding tokenizer. For our current release we support the following model architectures:
MII currently supports over 20,000 models across three popular model architectures. We plan to add additional models in the near term, if there are specific model architectures you would like supported please [file an issue](https://github.com/microsoft/DeepSpeed-MII/issues) and let us know. All current models leverage Hugging Face in our backend to provide both the model weights and the model's corresponding tokenizer. For our current release we support the following model architectures:

model family | size range | ~model count
------ | ------ | ------
[llama](https://huggingface.co/models?other=llama) | 7B - 65B | 11,000
[llama-2](https://huggingface.co/models?other=llama-2) | 7B - 70B | 800
[mistral](https://huggingface.co/models?other=mistral) | 7B | 1,100
[opt](https://huggingface.co/models?other=opt) | 0.1B - 66B | 900
[falcon](https://huggingface.co/models?other=falcon) | 7B - 180B | 300
[llama](https://huggingface.co/models?other=llama) | 7B - 65B | 15,000
[llama-2](https://huggingface.co/models?other=llama-2) | 7B - 70B | 900
[mistral](https://huggingface.co/models?other=mistral) | 7B | 3,300
[mixtral](https://huggingface.co/models?other=mixtral) | 7B | 200
[opt](https://huggingface.co/models?other=opt) | 0.1B - 66B | 1,100

## MII Legacy Model Support

Expand Down
Loading