turboderp's picture
Update README.md
387ab96
|
raw
history blame
1.32 kB
EXL2 quants of [Mistral 8x7B Instruct v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
Supported in ExLlamaV2 0.0.11 and up
[2.40 bits per weight](https://huggingface.co/turboderp/Mixtral-8x7B-instruct-exl2/tree/2.4bpw)
[2.50 bits per weight](https://huggingface.co/turboderp/Mixtral-8x7B-instruct-exl2/tree/2.5bpw)
[2.70 bits per weight](https://huggingface.co/turboderp/Mixtral-8x7B-instruct-exl2/tree/2.7bpw)
[3.00 bits per weight](https://huggingface.co/turboderp/Mixtral-8x7B-instruct-exl2/tree/3.0bpw)
[3.50 bits per weight](https://huggingface.co/turboderp/Mixtral-8x7B-instruct-exl2/tree/3.5bpw)
[4.00 bits per weight](https://huggingface.co/turboderp/Mixtral-8x7B-instruct-exl2/tree/4.0bpw) (still uploading)
[5.00 bits per weight](https://huggingface.co/turboderp/Mixtral-8x7B-instruct-exl2/tree/5.0bpw)
[6.00 bits per weight](https://huggingface.co/turboderp/Mixtral-8x7B-instruct-exl2/tree/6.0bpw)
[8.00 bits per weight](https://huggingface.co/turboderp/Mixtral-8x7B-instruct-exl2/tree/8.0bpw) (still uploading)
[measurement.json](https://huggingface.co/turboderp/Mixtral-8x7B-instruct-exl2/blob/main/measurement.json)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/Z86yJWJMzT4gljf27mmTF.png)