Downloads · 30 days
0
GenerativeMagic/Llama-Engineer-Evol-7b-GGML
Llama-Engineer-Evol-7b-GGML is a text generation model from GenerativeMagic. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-sa-4.0.
Downloads · 30 days
0
Access
Public
Updated Jul 26, 2023
Repo size
3.8 GB
Likes
2
Public
Click a slice to open those files.
.bin3.8 GB · 100%
From the Hugging Face model README

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