-
### 📚 The doc issue
Hey vLLM team it looks like there is added support for llava 1.5 but there are no docs or examples on how to use it via the api server. Are there any reference examples? For using…
-
Hello, thank you for your great work!
We are currently exploring the utilization of radio as a vision encoder for vision language models. In our specific setup, we employ [SigClip](https://huggingfac…
-
### System Info
- `transformers` version: 4.44.2
- Platform: Linux-4.15.0-76-generic-x86_64-with-glibc2.27
- Python version: 3.12.4
- Huggingface_hub version: 0.23.4
- Safetensors version: 0.4.3
…
-
Hi, really nice work! I have a question about the ARO results of LLava and miniGPT4 reported in the paper. Since these model are generative VLMs and obtain really high scores, I wonder how are the sco…
-
Thank you so much for open sourcing the code and models. It is very helpful! I was wondering how to extract the last hidden outputs from the models.
-
**Describe the bug**
When the model fits on a single GPU, how does Deepspeed ZeRO stage 1 compare with DDP? In my experiments, the Deepspeed ZeRO stage 1. I see that my overall loss training progress…
-
### System Info
- `transformers` version: 4.39.1
- Platform: Linux-5.19.0-051900rc6-generic-x86_64-with-glibc2.35
- Python version: 3.9.18
- Huggingface_hub version: 0.21.1
- Safetensors version:…
-
Fellow MiniCPM-Llama3-V 2.5 project authors, a few days ago I discovered a shocking fact.There is a large amount of work in the llama3-V (https://github.com/mustafaaljadery/llama3v) project that is su…
-
-
Excellent work:)
But I can`t fine the data_util file in the lasted version..
And I would …