AI - AI Dynamics

Llama v2 70B: Fastest Online Demo Access Guide

By

–

19 July 2023 0h09

the easiest and fastest place to try the new largest Llama v2 70B online seems to be here at the moment afaict with good latency: https://
huggingface.co/spaces/ysharma
/Explore_llamav2_with_TGI
… Post other online demo of the 70B in the replies here

→ View original post on X — @thom_wolf

19 July 2023

LangSmith Integration Enables Visibility Into LangChain API Calls

By

@hwchase17

–

19 July 2023 0h05

One of the cool things about LangSmith is it integrates seamlessly with all projects built on top of or integrated with LangChain Particularly useful for seeing what calls are actually getting made + the prompts that are used! Here is the call that PandasAI makes:

→ View original post on X — @hwchase17

19 July 2023

Try Llama 70B Model Online Without Download Installation

By

@thom_wolf

–

19 July 2023 0h01

Easiest way to try the 70B without download/install is here at the moment: https://
huggingface.co/spaces/ysharma
/Explore_llamav2_with_TGI
…

→ View original post on X — @thom_wolf

19 July 2023

New 70B Model Outperforms Open Source Language Models on Benchmarks

By

@aiatmeta

–

19 July 2023 0h01

Our new 70B model outperforms published results from other open sourced language models across external benchmarks such as MMLU, TriviaQA, GSM8K, AGIEval and more.

→ View original post on X — @aiatmeta

19 July 2023

Llama 2: Advanced Open Language Model with Expanded Context Length

By

@aiatmeta

–

19 July 2023 0h01

Llama 2 is a step forward for commercially available language models and open innovation in AI. These new models were pretrained on 2T tokens, and have double the context length when compared to the original release of Llama. Download Llama 2 https://
bit.ly/3Q45cDS

→ View original post on X — @aiatmeta

19 July 2023

AI Transforming Biology: Digital Speed Science Advancement

By

@demishassabis

–

18 July 2023 23h52

I’ve always been passionate about AI’s ability to transform the field of biology – it's just one example of AI enabling science at digital speed. We’re already starting to see the positive impact of this work. Much more to come.

→ View original post on X — @demishassabis

18 July 2023

Fine-tune LLM models on your own infrastructure

By

@alexandr_wang

–

18 July 2023 23h45

you can fine tune on your own machine / infrastructure, in which case you'll definitely own the model! https://
scaleapi.github.io/llm-engine/gui
des/self_hosting/
…

→ View original post on X — @alexandr_wang

18 July 2023

SimPer: Self-Supervised Contrastive Learning for Periodic Data

By

@googleai

–

18 July 2023 23h32

SimPer is a self-supervised contrastive framework for learning periodic information in data, while improving data efficiency and generalization to distribution shifts. Check it out and copy the code → https://t.co/P7eEpf1AKq pic.twitter.com/40G18nzKeu
— Google AI (@GoogleAI) 18 juillet 2023

SimPer is a self-supervised contrastive framework for learning periodic information in data, while improving data efficiency and generalization to distribution shifts. Check it out and copy the code → https://
goo.gle/3XZcFWC

→ View original post on X — @googleai

18 July 2023