openchat
openchat copied to clipboard
imoneoi
OpenChat: Advancing Open-source Language Models with Imperfect Data
Is it possible for @imoneoi or others to add more info to the training section in ReadMe? Like these items: 0. Create some toy data files 1. Train OpenChat using...
In the section of Request example in ReadMe, there is a Mathematical Reasoning Mode. How can we specify "condition": "Math Correct" when using Web UI https://openchat.team/ ?
There is a paper: Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models from UCLA. There seems a similarity between Self-Play Fine-Tuning and C-RLFT. I am curious if SPIN...
An API token is required to make requests. How can I get an api token after deploying a server to access the server?
Is it possible to distill the model to only English - in a similar say to whisperdistill? would this lower the size and increase speed?
Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> See above for output. note: This error originates from a subprocess, and is likely not a...
the model of Pre-tokenized dataset openchat_v3.2_super.train.parquet is Llama2 or Mistral?
Hi, I am interested in evaluating OpenChat (https://github.com/evalplus/evalplus/issues/60, https://github.com/evalplus/evalplus/issues/61) and want to understand what could be a minimal and self-contained HuggingFace example for me to follow. cc: @imoneoi
## Environment - `uname -a` outputs: ``` Linux remote-host 5.15.0-87-generic #97-Ubuntu SMP Mon Oct 2 21:09:21 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux ``` - GPU: 8xA800 80GB ## Problem When...
I am looking for something like this, so I can run this on a single 3090. docker run --gpus 1\ -e HF_TOKEN=$HF_TOKEN -p 8000:8000 \ ghcr.io/mistralai/mistral-src/vllm:latest \ --host 0.0.0.0 \...
