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

[DOCS] Fix typo for llava next docs (#29829)

Browse Source 
Fix typo for llava next docs
This commit is contained in:
Billy Cao
2024-03-24 02:32:31 +08:00
committed by GitHub
parent c5f0288bc7
commit dafe370255
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/model_doc/llava_next.md
View File

@@ -101,7 +101,7 @@ print(processor.decode(output[0], skip_special_tokens=True))
The model can be loaded in 8 or 4 bits, greatly reducing the memory requirements while maintaining the performance of the original model. First make sure to install bitsandbytes, `pip install bitsandbytes`` and make sure to have access to a CUDA compatible GPU device. Simply change the snippet above with: The model can be loaded in 8 or 4 bits, greatly reducing the memory requirements while maintaining the performance of the original model. First make sure to install bitsandbytes, `pip install bitsandbytes`` and make sure to have access to a CUDA compatible GPU device. Simply change the snippet above with:
```python ```python
from transformers import LlavaNextForConditionalGeneration, BitsandBytesConfig from transformers import LlavaNextForConditionalGeneration, BitsAndBytesConfig
# specify how to quantize the model # specify how to quantize the model
quantization_config = BitsAndBytesConfig( quantization_config = BitsAndBytesConfig(