Anyscale Endpoints enables AI application developers to easily swap closed models for the Llama 2 models — or use open models along with closed models in the same application.
OPEN SOURCE
-
Meta and Anyscale collaborate on Llama 2 developer opportunities
By
–
Thanks for the collaboration — we're excited for what developers will be able to do with Llama 2 through Anyscale Endpoints!
-
Hugging Face Leaders Recognized in Time’s 100 AI List
By
–
Mind-blowed to see both my amazing co-worker @mmitchell_ai and awesome co-founder @ClementDelangue selected in Time's 100 AI Super proud of what @huggingface is creating for the community (PS lot of great people missing from the list as well)
-
Adding Human Readable Names to LangChain Components
By
–
If you have long chains written with LangChain Expression Language, it can be really helpful to add human readable names to each component We've now got a cookbook for that!
-
Self-Alignment with Instruction Backtranslation for LLMs
By
–
Self-Alignment with Instruction Backtranslation by Xian Li, Ping Yu, Chunting Zhou, Timo Schick, Luke Zettlemoyer, Omer Levy, @jaseweston
, Mike Lewis https://
arxiv.org/abs/2308.06259 -
Halo: Reducing Hallucinations in Weak Open-Source LLMs
By
–
Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models by Mohamed Elaraby, Mengyin Lu, Jacob Dunn, Xueying Zhang, Yu Wang, Shizhu Liu
-
OctoPack: Instruction Tuning Code Large Language Models
By
–
OctoPack: Instruction Tuning Code Large Language Models, by @Muennighoff @sivil_taram @RandyZebaze @qinkai1028 @huybery @terryyuezhuo @_s_w_a_y_a_m_ @XiangruTang @lvwerra @ShayneRedford https://
arxiv.org/abs/2308.07124
v1
… -
Meta Publishes Code Llama Research Paper on AI Foundation Models
By
–
As part of our continued belief in the value of an open approach to today's AI, we've published a research paper with more information on Code Llama training, evaluation results, safety and more. Code Llama: Open Foundation Models for Code https://
bit.ly/44DEqpj -
Jais: Open-Source Arabic NLP Model Performance Breakthrough
By
–
Cerebras welcomes a guest post from Inception CEO Andy Jackson about our recent work together on Jais, the world’s best-performing open-source Arabic model The post details the model architecture, data, hardware, and performance evaluations Read here: https://
cerebras.net/blog/jais-a-ne
w-pinnacle-in-open-arabic-nlp
… -
LangChain Streamlit Hackathon Project Ideas and Resources
By
–
For other project ideas, we wrote a little blog highlighting some here: https://
blog.langchain.dev/streamlit-llm-
hackathon-kickoff-and-projects-wed-love-to-see-2/
… There's also the AMAZING langchain streamlit github repo: