open-compass/MixtralKit
A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI
This toolkit helps AI developers and researchers quickly set up and run tests on the Mixtral-8x7B large language model. It takes the Mixtral model as input and provides performance metrics across various benchmarks, allowing users to understand its capabilities for tasks like reasoning, common sense, and coding. This is for professionals who build or evaluate large language models.
771 stars. No commits in the last 6 months.
Use this if you need to quickly perform inference and evaluate the performance of the Mixtral-8x7B model on a range of common benchmarks.
Not ideal if you are looking for a general-purpose toolkit for training or fine-tuning diverse large language models beyond Mixtral-8x7B.
Stars
771
Forks
75
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/open-compass/MixtralKit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mistralai/mistral-inference
Official inference library for Mistral models
dvmazur/mixtral-offloading
Run Mixtral-8x7B models in Colab or consumer desktops
vicuna-tools/vicuna-installation-guide
The "vicuna-installation-guide" provides step-by-step instructions for installing and...
pleisto/yuren-13b
Yuren 13B is an information synthesis large language model that has been continuously trained...
hkproj/mistral-llm-notes
Notes on the Mistral AI model