Open Source Summit Japan 2023: Day 2
OPEN SOURCE
-
Follow Top NLP Researchers: INSTRUCTOR Embedding Model Creators
By
–
here are two awesome researchers you should follow: @WeijiaShi2 at UW and @wzhao_nlp at Cornell!! some of their recent work: weijia shi (
@WeijiaShi2
): – built INSTRUCTOR, the embedding model that lots of startups / companies use (
http://
arxiv.org/abs/2212.09741)
– proposed a more -
101 Guide to Fine-tuning Open-source LLMs
By
–
Here's your 101 Guide to #Fine-tuning Open-source #LLMs thanks to @AnalyticsVidhya and @predibase ML Engineer, @grg_arnav https://
pbase.ai/417L9rA -
Open vs Closed AI: Governance Without Blame Culture
By
–
when did having someone to blame become a requirement to advance in this field? governance and guardrails is needed but closed ai will never get us there as it is will be "closed" – with open ai, only thing you have to need is smart people on all the sides. and if you believe
-
Businesses Switch to Open-Source LLMs for Cost-Effective Performance
By
–
We’re seeing more and more businesses switch from closed to open-source language models. You can fine-tune models like Llama 2 and Mistral to perform better than GPT-4 on particular tasks with a much smaller, cheaper model.
-
Language Models Drive Growth for Replicate After Llama 2 Release
By
–
Although we got our start in generative images, language models are where we see most of our growth. The week Llama 2 came out was our biggest week of growth ever.
-
Stable Diffusion: From Toy to Open-Source Image Generation Tool
By
–
Last year, Stable Diffusion was released. It was an open-source image generation model that caught the imagination of tinkerers. At the start, it felt like a toy. It was just people tinkering around and seeing what was possible.
-
Replicate Raises $40M Series B to Expand Open-Source AI Business
By
–
Businesses are building on open-source AI. But we’ve only reached a tiny fraction. That's why we raised a $40M Series B. Open-source is open for business
-
Testing Combined Open Source Strategies for Performance
By
–
Or pick up where we left off testing the open source strategies at this repo. How would it perform if you combine strategies?
-
GPT-4 and Llama Performance Comparison on Tool-Calling Benchmark
By
–
Unsurprisingly, GPT-4 with tool-calling ability performed the best on this benchmark, but Llama, even when not fine-tuned, performed well . See the comparison at this link: https://
smith.langchain.com/public/00f4444
c-9460-4a82-b87a-f50096f1cfef/d/compare?selectedSessions=0c022691-a7ac-4545-b2bc-58aab2d476e8d522dbfc-c09b-45a9-b11e-26aa95a3555a
…