balcklive
balcklive
> Can you try downgrading `transformers` to 4.21.0? I tried, another bug happend: Traceback (most recent call last): File "/home/ubuntu/./ColossalAI/applications/Chat/inference/server.py", line 10, in from llama_gptq import load_quant File "/home/ubuntu/ColossalAI/applications/Chat/inference/llama_gptq/__init__.py", line...
8*V100 32G got the same OOM
when would this MultiGPU support be available? Really looking forward to it.
@PierpaoloSorbellini HI, thank you for your reply, I tried what you said. 1. "enabled": false, (under fp16),: the error no longer appeared, but the GPU memory consumption is till high,...
My bachszie is always 1, I can't lower it anymore. Yes I am using one GPU, but my GPU memory capacity got 24G, I think it's supposed to be able...
It's REWARD model, As I mentioned in issue #281 , my config file specify the model type as opt-125m, but it actually is a gpt2 model. Deepspeed module can compress...
@fatwang2 老铁，这个dify2openai和chatgpt-on-wechat放在一起跑通过吗？我试了好像不行啊，我的配置文件如下： "channel_type": "wx", "model": "dify", "open_ai_api_key": "xxxxx", "proxy": "http://myipAddress:3000/v1/chat/completions", "hot_reload": false, 报错内容如下： [WARNING][2024-07-07 23:03:23][chat_gpt_session.py:86] - num_tokens_from_messages() is not implemented for model dify. Returning num tokens assuming gpt-3.5-turbo. [WARNING][2024-07-07 23:03:23][chat_gpt_bot.py:150]...
@fatwang2 哪个变量啊
> 这是 apibase，不是 proxy balcklive ***@***.***>于2024年7月8日 周一22:42写道： > […](#) > @fatwang2 哪个变量啊 — Reply to this email directly, view it on GitHub , or unsubscribe . You are receiving this...
> ng on your side. 8bit quantization gives me dec which river is the longest river on the planet?setющихatur cubefunctionMatrix aprilприяalia Database)(()hel head Frauen Rank ocupрии Saf # hartmlPairobjectutopreiscompany MillerSpeedścieanhaorders...