OpenChatKit
OpenChatKit copied to clipboard
togethercomputer
I propose this pull request for convert_to_hf_gptneox.py so it supports conversion to the HF format for the special case of non-distributed training, so with n_stages = 1
I see in the announcement you mentioned moderation model. But I haven't seen any documentation how to use that. Do you have anything related to it?
Hello I tried this on your website and asked the probability that 911 was an inside job for fun. Was told this is not allowed? Is there an easy way...
I am trying to monitor training for the OpenChatKit-7B model by increasing the number of iterations etc. I want to monitor the quality of the training with Tensorboard but have...
**Describe the bug** Running the Pythia-7B fine-tune script on 4 x A10 (24GB each). Seems like issue with seq len: _``` Token indices sequence length is longer than the specified...
Hi, I had tested many model , and came across a very good model. It is possible to be able to loading or converting ggml model ggml-vicuna-13b-1.1-q4_2.bin or use huggingface...
I want to know how to avoid oom when fine-tuning the 20B model, only fp16？
1545
**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: 1. Go to '...' 2. Click on '....' 3. Scroll...
when i use this model ask some question while a moment later happens the memory is not enough WeTraceback (most recent call last): File "/export/openChatKit/openChatKit/inference/bot.py", line 285, in main() File...
mamba env create -f environment.yml Traceback (most recent call last): File "/Users/ilya/anaconda3/bin/mamba", line 7, in from mamba.mamba import main File "/Users/ilya/anaconda3/lib/python3.10/site-packages/mamba/mamba.py", line 49, in import libmambapy as api File "/Users/ilya/anaconda3/lib/python3.10/site-packages/libmambapy/init.py",...
