HeMuling

Results 10 issues of HeMuling

I found that the model of LLaMA-7B shut down unexpectedly when the number of tokens in prompt reaches some value, this value is approximately to be 500 this cannot be...

I got this message when trying to upload an image ``` Cannot upload file IMG_5549png: The backend services were not able to communicate with each other. ``` ![](https://cdn.discordapp.com/attachments/1088371919725793360/1098583992388821003/image.png)

bug
web app

update to allow BAM to handle case when input height not equals input width

从pip install下载的metagpt版本落后于github上的版本 范例文件:`metagpt/utils/token_counter.py` pip install 下载的metagpt不包含`gpt-4o`,而github上的版本则包含 建议:更新pip源或更改doc中安装方式

Error in converting Markdown to PDF, after clicking `download pdf`, the local host page will reload and content will be cleared. in terminal shows: ``` ----- WeasyPrint could not import...

I tried to perform next token prediction task using the pretrained model `hyenadna-small-32k-seqlen-hf`, and I found the result not so solid. Here' the code I tried: ``` from transformers import...

I've noticed that in readme you said "Compatible with any OpenAI API models", is there any guide for that?

Install the latest version via docker compose on mac, the log shows: ``` > [gpt-researcher install-browser 2/2] RUN apt-get update && apt-get install -y gnupg wget ca-certificates --no-install-recommends && wget...

I ran single ocr on M1 chip with 16GB of ram, set `--batch_multiplier` to 2, `--max_pages` to 14, and I encountered this: ``` Loaded detection model vikp/surya_det3 on device mps...

### Installation Method | 安装方法与平台 Docker-Compose(Windows/Mac) ### Version | 版本 Latest | 最新版 ### OS | 操作系统 Mac ### Describe the bug | 简述 连接超时,显示KeyError: 'gpt-4o-mini',换用gpt-4o 或 gpt-3.5-turbo可以正常运行 配置: `docker-compose`中:...