tiger-wang

My GPU is only 30%~50% utilized when running this project, it's too slow!

Can it be used in Windows and Python virtual environments?

4

windows11, python3.8, pycharm2022. ``` D:\AppInstall\Python38\python.exe: No module named pip Command '['python', '-m', 'pip', '--default-timeout', '45', 'install', 'mmcv==2.0.0rc4']' returned non-zero exit status 1. ``` `D:\AppInstall\Python38\python.exe` is not the virtual environment I...

Dear pion/webrtc team, I hope this message finds you well. I wanted to start by expressing my appreciation for the fantastic work you've done with the pion/webrtc project. It's an...

能在浏览器环境下运行吗？

1

能在浏览器环境下运行吗？

你好，请问各个包的版本是多少？我安装了报错了，应该是版本不兼容

我的数据量太小，不想从头开始训练。

What model should be used here？

2

File "E:\work\work_py\TinyGPT-V\minigpt4\conversation\conversation.py", line 16, in tokenizer = AutoTokenizer.from_pretrained('/root/autodl-tmp/phi-new') ... OSError: Incorrect path_or_model_id: '/root/autodl-tmp/phi-new'. Please provide either the path to a local folder or the repo_id of a model on the...

我希望能知道服务端的http api接口，这样我可以方便地自己写前端。

3

我希望能知道服务端的http api接口，这样我可以方便地自己写前端。

I would like to add a function: ``` func KeyCode2String(key int) (k string, err error) { for keyStr, keyCode := range keyNames { if keyCode == C.int(key) { return keyStr,...

transformers怎么使用gguf？

1

我想使用int4,发现只有gguf的。然后我下载了`llama3.1_8b_chinese_chat_q4_k_m-shareAI.gguf`。 从这里下载的：https://hf-mirror.com/shareAI/llama3.1-8b-instruct-dpo-zh 然后使用transformers。 ``` from transformers import AutoTokenizer, AutoModelForCausalLM model_id = ".\\models\\llama3.1-8b-instruct-dpo-zh" filename = "llama3.1_8b_chinese_chat_q4_k_m-shareAI.gguf" tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename) model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename) ``` 运行后报错： ``` Traceback (most recent call...