This is proof of concept of what LLM's are able to do when fine-tuned for code generation and understanding.
The base model is based on OpenLlama-3b and can be found [here](https://huggingface.co/psmathur/orca_mini_3b) and trained using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl/tree/main)
Next I'll show some examples of what the model is currently capable of.
I have edited the quotes to be able to show the prompts correctly here the model writes proper markdown.
The first sample shows a non-trivial example of the model generating code.
(Depending on the complexity of the required task the generated code might not work. For example, making the model write code to move the square
around has proven to be quite difficult.)
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Write Python code to draw a square on the screen using Pygame.
### Response:
Sure, here's a Python code to draw a …
