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
LLMS
-
Llama v2 70B: Fastest Online Demo Access Guide
By
–
-
Try Llama 70B Model Online Without Download Installation
By
–
Easiest way to try the 70B without download/install is here at the moment: https://
huggingface.co/spaces/ysharma
/Explore_llamav2_with_TGI
… -
New 70B Model Outperforms Open Source Language Models on Benchmarks
By
–
Our new 70B model outperforms published results from other open sourced language models across external benchmarks such as MMLU, TriviaQA, GSM8K, AGIEval and more.
-
Llama 2: Advanced Open Language Model with Expanded Context Length
By
–
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 -
Fine-tune LLM models on your own infrastructure
By
–
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/
… -
Launch Partner for Llama 2 Announcement
By
–
we were proud to be a launch partner of LLAMA 2 and help do our part @scale_AI
-
Latent Space Pod Hosts Llama 2 Snap Discussion Today
By
–
FYI: we are holding a snap @latentspacepod on Llama 2 at 4pm PT today! https://
x.com/i/spaces/1nAKE
rrWzBZGL
… ft. @natolambert @simonw @BornsteinMatt and ofc @fanahova and @swyx
! -
Meta Databricks Partner on Llama 2 Open Source LLM
By
–
We're excited to partner with Meta on the new #opensource state-of the-art LLM, Llama 2 With new models including 7B, 13B and 70B, Llama 2 accelerates LLM research work & empowers enterprises to build their own #generativeAI applications. Learn more: https://
dbricks.co/3rAyxLV -
LangSmith Platform Complete Walkthrough Webinar
By
–
We'll be going live in ~30 min to do a complete walkthrough of our new LangSmith platform and answer any questions We'll be joined by @charles_irl – our favorite webinar guest – to help explore all that it has to offer
-
Llama 2 Safetensors Format Standardization by Hugging Face
By
–
Fun little inside aside here, Llama 2 is in safetensors format. Hugging face has done a ton of work to standardize that so that's a pretty big stamp of approval.