Alexander Wu

@AnonDevSUS How did you install it? It seems to be a problem with chroma. I wonder if the installation of chroma was successful?

chroma did encounter some problems before. Maybe it would be better to consider removing this dependency and only doing the import when needed. @better629 What do you think?

@voidking can you help us test 3.12? If successful, maybe we can add a versioned ci/cd script that does not run by default, but can be triggered manually

@kripper We have more experiments and effect updates. But frankly speaking, this is a relatively complex scientific research problem. After the next few weeks of experimentation, we will standardize the...

@kripper You can look into SWE-bench if you are interested. If you want to participate in performance optimization, I personally welcome it

@kripper I mean: https://github.com/princeton-nlp/SWE-bench this dataset. We are testing and optimizing it

@ming188199 Can you try it again?

@redlion99 I have added the corresponding configuration. Can you take a look at the relevant PR and test whether it solves your problem?

@Kohl-Watson Models such as llama2 tend to fail to follow instructions at small scales (e.g. 13B/7B). This problem is known and needs to be scaled up to solve the problem...

Since no reply was received, this issue is closed, if needed open it again