-
Hi, Merve!
I noticed that you are comparing multilingual SigLIP with NLLB-CLIP. But there actually is a newer version of NLLB-CLIP that uses the SigLIP vision encoder! It is integrated into OpenCLI…
-
modelscope.hub.errors.FileIntegrityError: File /home/apple/.cache/modelscope/hub/._____temp/qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4/model-00002-of-00002.safetensors integrity check failed, expected sha256…
-
SAM can be used with Siglip/CLIP
For example, [Vary](https://github.com/Ucas-HaoranWei/Vary) uses SAM+CLIP, and [Deepseek-VL](https://github.com/deepseek-ai/DeepSeek-VL) uses Siglip+SAM.
Would y…
-
I redownload this repo,and tried `transfoemers` version:`4.40.0.dev`、`4.40.0`、`4.41.2`,the result is still `['']`.
some thing i do include:
All weight i use is local weight.below is my change.
1. `…
-
I get this error while try use moondream2 with CUDA, low memory is ON RTX 4070.
```
Error occurred when executing LoadImage2TextModel:
Unknown model (vit_so400m_patch14_siglip_384)
File "/ho…
-
### 🚀 The feature, motivation and pitch
Having good basic pytorch support for inferencing LLMs is key to continued success of pytorch. Vision LLM models tend to have uneven support on mainstream infe…
-
### System Info
- `transformers` version: 4.38.2
- Platform: Linux-4.18.0-477.27.1.el8_8.x86_64-x86_64-with-glibc2.28
- Python version: 3.10.13
- Huggingface_hub version: 0.21.4
- Safetensors ver…
-
支持自定义视觉编码器么(llava-llama3)?
例如将clip换成siglip?
该如何实现?哪些代码需要修改?
-
Congrats for solving the Mode Switching issue with radio 2.5 ! Now all the heads of the am-radio dragon breath fire at the same time! 🔥🔥🔥
Now I wonder what is the future of this project and if ther…
-
Hi,
I noticed something when loading checkpoints other than the pretrained ones and wanted to understand what the intended behavior was. For example, loading and saving a B32 pretrained checkpoint…