elven2016

models suport for vicuna

3

**Description** the support models are [Pythia][OPT][GALACTICA][GPT-J 6B] ，is there any plan support for the vicuna model？

### Describe the bug Training tab, select the lora from the menu in order to copy parameters ,the page get error, the terminal find this error Traceback (most recent call...

A100 80 G fine tune llama-65b-hf got CUDAout of Memory

12

when i strart train， it works fine，the parameters as follows  and the gpu usage is as follows：  but when complete 17% it exits，the logs is here： 

ubuntu can not launch jan webui app

6

**Describe the bug** after install the deb pkg succesful， the app webui not appear **Steps to reproduce** Steps to reproduce the behavior: 1. download the ubuntu server version deb install...

FATAL:credentials.cc(127)] Check failed: . : Permission denied (13)

1

can not startup ，when exec the command npm start ，it appears the following error npm start > [email protected] start > electron . [26406:0612/201648.101773:FATAL:credentials.cc(127)] Check failed: . : Permission denied (13)...

already quantize to 4bit and get the model pyllama-7B4b.pt，but can not run in RTX3080. report torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 86.00 MiB (GPU 0; 10.00 GiB total capacity; 9.24 GiB already allocated;

2

the error is as the follow： python webapp_single.py --ckpt_dir $CKPT_DIR --tokenizer_path $TOKENIZER_PATH Traceback (most recent call last): File "/home/xxxx/chatllama/pyllama/apps/gradio/webapp_single.py", line 80, in generator = load( File "/home/u/chatllama/pyllama/apps/gradio/webapp_single.py", line 42, in...

data目录下hg上llm的元数据文件p0_models.jsonl怎么获取？huggingface上的model增加了很多，这个上面过滤了下只有673个，请问下导出最新的这个数据？

twiter can not download AttributeError: 'DataFrame' object has no attribute 'created_at' 

执行pnpm optimize failed

2

执行pnpm optimize failed，ip.sql没这个文件