I recently conducted a test using Guanaco 33B, with internet access enabled (EdgeGPT, with the ‘always search’ setting checked). To my surprise, I found that Guanaco outperformed ChatGPT (non-paid version), Bing, and Phind.com in generating code. I compared the code generation results using the same prompts across all platforms, and Guanaco consistently delivered superior coding output.

In order to optimize the performance of Guanaco, I modified the instruction template by creating an additional YAML file for guanaco-chat. The changes included the following parameters:

### Human:

### Assistant:

context:" A chat between... (vicuna like)

I adjusted the values for max_new_tokens to 289, temp to 0.75, and top_p to 0.85. All other parameters remained the same as LLaMA-Precise.

If anyone has had experience using Guanaco specifically for code generation, I would greatly appreciate any insights or feedback. Personally, I find it to be an incredibly useful assistant.