Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B(phind.com)

737 points by rushingcreek 3 years ago | 258 comments

Phind blog post announcing fine-tuned CodeLlama-34B models that score 67.6% and 69.5% pass@1 on HumanEval, beating GPT-4's reported 67%.

Tuning and Testing Llama 2, Flan-T5, and GPT-J with LoRA, Sematic, and Gradio(sematic.dev)

87 points by josh-sematic 3 years ago | 19 comments

We fine-tuned Llama 405B on AMD GPUs(publish.obsidian.md)

452 points by felarof 2 years ago | 87 comments

Felafax blog post describing how they fine-tuned Llama 3.1 405B on 8 AMD MI300X GPUs using JAX, covering parameter sharding and LoRA.

A simple guide to fine-tuning Llama 2(brev.dev)

253 points by samlhuillier 3 years ago | 44 comments

Show HN: FinetuneDB – AI fine-tuning platform to create custom LLMs(finetunedb.com)

136 points by felix089 2 years ago | 64 comments

Guide to running Llama 2 locally(replicate.com)

573 points by bfirsh 3 years ago | 153 comments

Replicate blog post explaining how to run Meta's Llama 2 model locally on M1/M2 Macs, Windows, Linux, and phones without an internet connection.