SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Docs] Fix un-rendered images (#25561)

Browse Source 
fix un-rendered images
This commit is contained in:
Younes Belkada
2023-08-17 12:08:11 +02:00
committed by GitHub
parent 8992589dd6
commit e7e9261a20
4 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/en/perf_infer_gpu_one.md
View File

@@ -104,12 +104,12 @@ Note that this feature can also be used in a multi GPU setup.
From the paper [`LLM.int8() : 8-bit Matrix Multiplication for Transformers at Scale`](https://arxiv.org/abs/2208.07339), we support Hugging Face integration for all models in the Hub with a few lines of code.
The method reduces `nn.Linear` size by 2 for `float16` and `bfloat16` weights and by 4 for `float32` weights, with close to no impact to the quality by operating on the outliers in half-precision.
![HFxbitsandbytes.png](https://s3.amazonaws.com/moonup/production/uploads/1659861207959-62441d1d9fdefb55a0b7d12c.png)
![HFxbitsandbytes.png](https://cdn-uploads.huggingface.co/production/uploads/1659861207959-62441d1d9fdefb55a0b7d12c.png)
Int8 mixed-precision matrix decomposition works by separating a matrix multiplication into two streams: (1) a systematic feature outlier stream matrix multiplied in fp16 (0.01%), (2) a regular stream of int8 matrix multiplication (99.9%). With this method, int8 inference with no predictive degradation is possible for very large models.
For more details regarding the method, check out the [paper](https://arxiv.org/abs/2208.07339) or our [blogpost about the integration](https://huggingface.co/blog/hf-bitsandbytes-integration).
![MixedInt8.gif](https://s3.amazonaws.com/moonup/production/uploads/1660567469965-62441d1d9fdefb55a0b7d12c.gif)
![MixedInt8.gif](https://cdn-uploads.huggingface.co/production/uploads/1660567469965-62441d1d9fdefb55a0b7d12c.gif)
Note, that you would require a GPU to run mixed-8bit models as the kernels have been compiled for GPUs only. Make sure that you have enough GPU memory to store the quarter (or half if your model weights are in half precision) of the model before using this feature.
Below are some notes to help you use this module, or follow the demos on [Google colab](#colab-demos).