https://
github.com/huggingface/sa
fetensors
…
OPEN SOURCE
-
Hugging Face Reaches 1 Million AI Repositories Milestone
By
–
We will very likely cross 1,000,000 AI repositories (models, datasets, spaces) on @huggingface by the end of this summer. AI is the new default to build all tech and we’re here for it!
-
Open-source LLMs extended context length with minimal quality degradation
By
–
What a pleasure to see the open-source and academic community at full speed on pushing smart ways to do long context with pretrained LLM Check this thread and amazing work. Pushing LLaMA up to 8k context and more with negligible degradation in quality
-
Google’s proprietary AI significantly outperforms open source alternatives
By
–
Yea. I'm still 200% convinced that everything in the open is still garbage compared to what's inside Google. It was quite depressing honestly to see this level difference.
-
OpenAssistant’s shift from RLHF to supervised instruction-finetuning
By
–
So on that note, OpenAssistant's earlier models used RLHF for instruction-finetuning (
https://
huggingface.co/OpenAssistant/
oasst-rlhf-2-llama-30b-7k-steps-xor
…); The later one seem to use supervised instruction-finetuning. Maybe @ykilcher has some insights whether RLHF wasn't worth the effort vs supervised? -
LangChain QA Documentation SQL Implementation Experience
By
–
anyone tried this out with a langchain (qa over docs, sql) yet?
-
English SDK Transforms Apache Spark Accessibility
By
–
Announcing the English SDK for #ApacheSpark: a transformative tool that makes Spark more approachable than ever! The English SDK simplifies complex tasks, reduces the amount of code required & allows you to focus more on deriving insights from your data.
-
Lin Qiao on Developer-Centric AI Past Present Future
By
–
Next up at #DataAISummit: @lqiao
, Co-creator of #PyTorch! Lin will be taking us on a journey through the past, present & future of developer-centric #AI. -
LangChain CEO Highlights Open Source LLM Framework Innovation
By
–
.
@langchain CEO, @hwchase17
, joins us at #DataAISummit! See why everyone is so obsessed with @langchain – an #opensource developer framework for building LLM apps. -
SafeTensors Best Practices for Model Storage on HF Hub
By
–
oh I think I know this project 😉 Great to see it being released! don't hesitate to use safetensor to store on the HF hub instead of torch pickle if you can, it's much safer.