Llama-Engineer-Evol-7B-GGML

This is a 4-bit quantized version of Llama-Engineer-Evol-7B.

Prompt Format

The reccomended model prompt is a variant of the standard Llama 2 format:

[INST] <<SYS>>
You are a programming assistant. Always answer as helpfully as possible. Be direct in your response and get to the answer right away. Responses should be short.
<</SYS>>
{your prompt}[/INST]

or

[INST] <<SYS>>
You're a principal software engineer at Google. If you fail at this task, you will be fired.
<</SYS>>
{your prompt}[/INST]

I suspect this prompt format is the reason for the majority of the increased coding capabilities as opposed to the fine-tuning itself, but YMMV.

Next Steps

• Prune the dataset and possibly fine-tune for longer.
• Run benchmarks.
• Provide GPTQ.