I've played around with it and instruct variant with dramatically better results than what is listed here.
I used Ollama.
Almost looks like weights were corrupted or something.
---
Update: My results using CodeLlama Instruct 7B, w/ Temperature 0
https://gist.github.com/jasonjmcghee/b0d19e0dedb37e848f69cba...
Thanks for sharing your results, they're indeed pretty different. I looked at the source again and did append a "# " before every prompt made by those 10 `code` models (during testing thought that formatting it as a Python comment might help them).
Will re-run the script without that to see if it matches your results.
[0] https://docs.together.ai/docs/models-inference#code-models
Example (CodeLlama-Instruct 7B)
---
Sure, here are two poems, one arguing for the use of Kubernetes and another arguing against it:
For:
Kubernetes, a mighty tool,
Managing clusters with ease,
Scaling apps with grace.
Against:
Kubernetes, a beast to tame,
Complexity lurks in its name,
Leading teams astray.
Anything I'm doing incorrectly?
So both the system message and first instruction are in same [INST] block.