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

[doc] fix typo (#27981)

Browse Source
This commit is contained in:
Stas Bekman
2023-12-12 12:32:42 -08:00
committed by GitHub
parent 78172dcdb7
commit 9936143014
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/perf_infer_gpu_one.md
View File

@@ -227,7 +227,7 @@ model.save_pretrained("saved_model")
bitsandbytes is a quantization library that includes support for 4-bit and 8-bit quantization. Quantization reduces your model size compared to its native full precision version, making it easier to fit large models onto GPUs with limited memory. bitsandbytes is a quantization library that includes support for 4-bit and 8-bit quantization. Quantization reduces your model size compared to its native full precision version, making it easier to fit large models onto GPUs with limited memory.
Make sure you have bitsnbytes and 🤗 Accelerate installed: Make sure you have bitsandbytes and 🤗 Accelerate installed:
```bash ```bash
# these versions support 8-bit and 4-bit # these versions support 8-bit and 4-bit