Downloads · 30 days
17
2% of all-time downloads
Mixtral-8x7B-Instruct-2bit
keyfan/Mixtral-8x7B-Instruct-2bit
Mixtral-8x7B-Instruct-2bit is a text generation model from keyfan. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This is 2-bit quantization of mistralai/Mixtral-8x7B-Instruct-v0.1 using QuIP
All-time downloads
826
Public
Repo size
24.3 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin12.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mixtral
- Access
- Public
- Created
- Dec 30, 2023
- Updated
- Dec 31, 2023
- SHA
- ccc3bf0b
Try a prompt
Model card
From the Hugging Face model README
This is 2-bit quantization of mistralai/Mixtral-8x7B-Instruct-v0.1 using QuIP#
Model loading
Please follow the instruction of QuIP-for-all for usage.
As an alternative, you can use vLLM branch for faster inference. QuIP has to launch like 5 kernels for each linear layer, so it's very helpful for vLLM to use cuda-graph to reduce launching overhead. BTW, If you have problem installing fast-hadamard-transform from pip, you can also install it from source
Perplexity
Measured at Wikitext with 4096 context length
| fp16 | 2-bit |
|---|---|
| 3.8825 | 5.2799 |
Speed
Measured with examples/benchmark_latency.py script at vLLM repo.
At batch size = 1, it generates at 16.3 tokens/s with single 3090.
- Task
- Text Generation
- Library
- transformers
- Type
- mixtral
- License
- apache-2.0
- Languages
- en
- Created
- Dec 30, 2023
- Updated
- Dec 31, 2023