HN Explorer

rsaha7

↗ HN profile [ 53.2 ms ] full profile

No user record in our sample, but rsaha7 has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.

  1. Show HN: Toolkit for LLM Fine-Tuning, Ablating and Testing (github.com)

    Hello all! Very happy to share this toolkit that allows you to fine-tune your choice of open-source LLMs on your data! The toolkit also allows you to run ablation studies across LLMs, prompt designs, training…

    14 points 21
  2. Show HN: Leverage Falcon 7B blog post (medium.com)

    Hi HN community, I wrote this short blog post on ways to leverage the LLM Falcon 7B. In this blog post I cover: - zero shot prompting - few shot prompting - Finetuning with QLoRA I evaluate how Falcon does on…

    1 points 0
  3. Show HN: finetune LLMs via the Finetuning Hub (github.com)

    Hi HN community, I have been working on benchmarking publicly available LLMs these past couple of weeks. More precisely, I am interested on the finetuning piece since a lot of businesses are starting to entertain the…

    80 points 17