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

Fix qwen2-vl-docs. (#37879)

Browse Source 
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
This commit is contained in:
湛露先生
2025-04-30 20:32:21 +08:00
committed by GitHub
parent 4eb6acc896
commit 4fc976779e
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/model_doc/qwen2_5_vl.md
View File

@@ -118,7 +118,7 @@ The example below uses [torchao](../quantization/torchao) to only quantize the w
```python ```python
import torch import torch
from transformers import TorchAoConfig, Gemma3ForConditionalGeneration, AutoProcessor from transformers import TorchAoConfig, Qwen2_5_VLForConditionalGeneration, AutoProcessor
quantization_config = TorchAoConfig("int4_weight_only", group_size=128) quantization_config = TorchAoConfig("int4_weight_only", group_size=128)
model = Qwen2_5_VLForConditionalGeneration.from_pretrained( model = Qwen2_5_VLForConditionalGeneration.from_pretrained(