Discover more from Coding with Intelligence
Shell-AI: a simple CLI to write your bash commands & more LLM news
Week 35 of Coding with Intelligence
I created a wrapper for my own use, I use it daily! Even on my Raspberry Pi :) tldr;
pip install shell-aithen run something like
shai terraform dry run thingyand it suggests three commands you can choose to execute or dismiss.
Here's the HF checkpoint: https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0
This paper describes a fine-tuning technique that was used by Code Llama to create the highly performant "Unnatural Llama" variant that showed GPT-4 level coding performance on HumanEval.
Impressive inference latency. The following numbers are achieved for Llama 2 70B (non-quantized). Time to first token: 553 ms, Successive tokens: 27.33 ms.
Want more? Follow me on Twitter! @ricklamers