Discover more from Coding with Intelligence
Open Source models take flight: fine-tuning, grammar decoding & stronger base models
Week 41 of Coding with Intelligence
This issue contains many resources related to using Open Source LLMs. You can do more useful things with Open Source LLMs than ever before. Have fun!
Explore the API surface for a glimpse of what's next.
Like other SERP (e.g. DuckDuckGo) tools in LangChain but more optimized for LLM use.
Be careful, this context window probably doesn't pay attention to all tokens.
Generating synthetic traces for LLM fine-tuning
Authors from UC Berkeley, University of Washington, UCSD, CMU, MBZUAI, USC
Are manual prompt writing days behind us? Evolutionary algorithms have historically been good at black box optimizations. This paper outlines how to build a meta prompting strategy where a system (EA based) optimizes the prompts against a performance metric. Video walkthrough available by Yannic Kilcher https://www.youtube.com/watch?v=tkX0EfNl4Fc
Prompting strategies for more faithful LLM model reasoning
Generate (few-shot) CoT examples and get the benefit of CoT prompting without the overhead of curating examples. Great prompt engineering result! Give this a read.
Exploration from Microsoft in unlearning information stored in LLM weights. Aka Robot Lobotomy.
Yes you read that right, diffusion models for text generation. The paper contains a plot showing it outperforms GPT2 on BLEU.
Building agents? Perhaps consider being compatible with the outlined protocol.
Want more? Follow me on Twitter! @ricklamers