Billy Cao
Billy Cao
After many hours of debugging, I finally got llava-v1.6-mistral-7b to work fully on SGLang inference backend. This PR adds the relevant instructions to README.md, which references a PR I made...
### Describe the issue Issue: Cannot launch SGLang demo on llava mistral 7b, vicuna 7b works Command: ``` CUDA_VISIBLE_DEVICES=0 python3 -m sglang.launch_server --model-path llava-v1.6-mistral-7b --tokenizer-path llava-v1.6-mistral-7b --port 30000 ``` Log:...
Randomly stops working. E.g. the process does not exits but trying to visit the page will not load
**Describe the bug** My server regularly gets port scanned and random HTTP attack attempts (see screenshot below), I believe this is very common. Glances seem to have been affected by...
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment:ubuntu 22.04 - 版本号/Version:Paddle:2.6 PaddleOCR:2.7.0.3 问题相关组件/Related components:PaddleOCR - 运行指令/Command Code:NA ``` zh_ocr = PaddleOCR( use_angle_cls=False, det_model_dir="paddle/Multilingual_PP-OCRv3_det_infer", rec_model_dir="paddle/ch_PP-OCRv4_rec_infer", lang="ch"...
### System Info - `transformers` version: 4.39.0 - Platform: Linux-5.15.133.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 - Python version: 3.10.12 - Huggingface_hub version: 0.19.4 - Safetensors version: 0.4.1 - Accelerate version: 0.28.0 - Accelerate config: not...
I have found the offsets here: https://github.com/aliencaocao/netease_cloudmusic_discord_rpc/blob/028ddf26778d57f7e1073c2325124fcb53f70fe9/src/main.py#L43 not a PR because this repo uses different offsets, so this is just a FYI to the author and other users. For V3.0.0.beta...
**Describe the feature** The original implementation does support and there is need to fine-tune the LLM only for some textual knowledge sometimes. Right now the repo says it only support...
Im not very sure how to do the UI part yet, need some time to learn gradio
Useful for automating prompt conversation.