-
Can't run llava next
```
export server_port=30002
export CUDA_VISIBLE_DEVICES="2,3"
python -m sglang.launch_server --model-path lmms-lab/llava-next-110b --tokenizer-path lmms-lab/llavanext-qwen-t…
-
It seems that vit is not saved when unfreeze_mm_vision_tower is True.
-
### System Info
NA
### Information
- [ ] Docker
- [ ] The CLI directly
### Tasks
- [X] An officially supported command
- [ ] My own modifications
### Reproduction
It is unclear how to query TGI…
-
I've tried running the code and found what looks like a bug in the benchmark script, I'm just diagnosing now
The traceback seems to point to the type of the `image` parameter at line 68:
```py
…
lmmx updated
8 months ago
-
Hi, sorry they're is not discussion tab so I have to set this thread here. Im training at this moment a dataset of 100 000 HD images using CogVLM 4 bits for a future SDXL checkpoint. I finished the c…
-
Hello.
First of all, thanks for providing LLaVA-Next training code.
I have a question.
In the readme file, you recommend to finetune the entire model.
Also, in the train.py, it tries to train th…
-
Hi, thanks for the great works~!
I just want to ask that in this [blog](https://llava-vl.github.io/blog/2024-04-30-llava-next-video/), it contains a "Video Detailed Description (Score)" metric. How t…
-
Thanks for your work. When I ran the inference script 'video_detail_description_eval_shard.sh' .I didn't find llava/eval/evaluate_benchmark_video_detail_description.py. I wonder if it's because I'm mi…
-
I've been trying to deploy the new LLaVA-NeXT with Sglang on Modal but not sure why I'm getting "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tun…
-
Hey there, I am interested in running VQAScore with another VLM, CogVLM (see [here](https://huggingface.co/THUDM/cogvlm-chat-hf)). I was looking at the guidelines on how to adapt to another VQA model …