FastChat
FastChat copied to clipboard
lm-sys
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
 ``` Human: what is up Assistant: hread水⊙ cabinetuetgruppeualsgtfür]] cosa Bedeut Initializeanno работы continentored auc族 Dok grantgc GoldOperation Couldbuild appearing Reformricstrittciendo ?? tutte namespaceResultasa...
Following the instructions to install: ``` pip3 install --upgrade pip pip3 install -e . ``` And then running the model resulted in the following error: ``` Traceback (most recent call...
it show this error: ModuleNotFoundError: No module named 'prompt_toolkit' but when i run pip install prompt_toolkit or pip install -U prompt-toolkit it say: Requirement already satisfied: prompt_toolkit in c:\users\asser\miniconda3\lib\site-packages (3.0.38)...
The new version of weights use upper case role names for the prompt: Example prompt (Weight v1.1) A chat between a user and an assistant. USER: Hello! ASSISTANT: Hello! USER:...
The model I trained cannot be loaded,The training code `torchrun --nnodes=1 --nproc_per_node=4 \ fastchat/train/train_mem.py \ --model_name_or_path \ --data_path \ --bf16 True \ --output_dir ./checkpoints \ --num_train_epochs 3 \ --per_device_train_batch_size 4...
Seeing many complaints about the required peak memory being too high. We would like to keep the peak memory of the following command be less than 8GB. ``` python3 -m...
 How can I troubleshoot the problem
Incorrect rendering makes the code looks ugly on our page: The fix is similar to https://github.com/lm-sys/FastChat/pull/396
Any plan for fine-tuning a 30B version? Either directly fine-tuning it or with Lora?
Hi, I found this error while trying to run it on my Mac M2 8GB, I hope you can help me, thanks. I don't have any other process running. Last...
