Checkpoint support is in the works: https://
github.com/Lightning-AI/l
it-gpt/issues/464
…
OPEN SOURCE
-
Checkpoint Support Development in Progress for Lit-GPT
By
–
-
CodeLlama-Python 34B finetuned on unnatural instructions
By
–
It's CodeLlama-Python 34B finetuned on 15,000 unnatural instructions. What's an unnatural instruction? Would like to see a few examples 😛
-
Open Tech in AI and Crypto: Key Insights
By
–
Great fireside chat on “The importance of open tech in AI and crypto” with @connerruhl of @StabilityAI and @jessepollak of @BuildOnBase moderated by @joey_debruin as part of the http://
100.Builders kick off! See below for highlights and check out the live chat here – -
RAGAS Framework for RAG Systems Evaluation with LangSmith
By
–
RAGAS is an awesome open-source framework for evaluating RAG systems We recently integrated LangSmith RAGAS for optimal ease of evaluation We're also doing a webinar on RAG evaluation with them in 5 minutes!!! Link to webinar and blog
-
HuggingFace Model Creators vs Prompt Engineering Hackers
By
–
To clarify, creators as in the developers posting models on HF, not the ones suggesting GPT hacks on whatever platforms
-
Hugging Face Raises $4.5B: Enterprise Growth and Creator Support
By
–
Got a chance to chat with Clement Delangue about Hugging Face’s new $4.5B valuation mega round. We talked spaces, breaking into enterprise, and ways to support AI “creators,” from outreach and communication to ideas for uses to support them via tips.
-
Meta Releases Code Llama, Advanced Open-Source Coding Model
By
–
Today we’re releasing Code Llama, a large language model built on top of Llama 2, fine-tuned for coding & state-of-the-art for publicly available coding tools.
— AI at Meta (@AIatMeta) 24 août 2023
Keeping with our open approach, Code Llama is publicly-available now for both research & commercial use.
More ⬇️Today we’re releasing Code Llama, a large language model built on top of Llama 2, fine-tuned for coding & state-of-the-art for publicly available coding tools. Keeping with our open approach, Code Llama is publicly-available now for both research & commercial use. More
-
CodeLlama 34B Significantly Improves Coding Performance Over Llama 2
By
–
Llama 2 is awesome, however, coding tasks were not its strong suite. (See HumanEval, a coding-related evaluation task from the paper Evaluating Large Language Models Trained on Code.) The new 34B CodeLlama model is twice as good as the original 70B Llama 2 model and closes the
-
Papers with Code bug fix deployed successfully
By
–
better late than ever, I onboarded onto the paperswithcode codebase and found the bug and made the fix and @rbstojnic graciously re-deployed the code. All instances like this should be correctly classified now (or over the next few days as the script runs through). Addendum:
-
Hugging Face Balances Enterprise Growth With Community Model Sharing
By
–
Part of the challenge for Hugging Face will be continuing to grow its enterprise core—an experience around models on Hugging Face with spaces and endpoints—while fostering its community that has uploaded more than 1 million models. As expected, GitHub is the model here.