Most interesting review of Llama 3 I've seen so far
LLMS
-
LLaMA 3 Long-Context Training Timeline Awaited
By
–
Great! Any timeline there? Waiting to really push hard on training LLaMA 3 till I can use long-context.
-
Perplexity Labs Launches Llama 3 Models with Search Integration
By
–
http://
labs.perplexity.ai and brought up llama-3 – 8b and 70b instruct models. Have fun chatting! we will soon be bringing up search-grounded online versions of them after some post-training. also available on pplx-api, and you get 5$ monthly API credits if you're already -
Llama 3 8B Performance Comparable to Llama 2 70B Model
By
–
The model card has some more interesting info too: https://
github.com/meta-llama/lla
ma3/blob/main/MODEL_CARD.md
… Note that Llama 3 8B is actually somewhere in the territory of Llama 2 70B, depending on where you look. This might seem confusing at first but note that the former was trained for 15T tokens, while the -
Flow Engineering with CodiumAI and LangChain LangGraph Webinar
By
–
Flow Engineering with CodiumAI & LangChain/LangGraph New Webinar Alert – tomorrow at 9 AM PT! https://
us06web.zoom.us/webinar/regist
er/WN_fVikSl9eQv68b3ZUdQgwzA#/registration
… "Flow Engineering" is a term that has been gaining in popularity recently. The first time it was mentioned as term was in @CodiumAI paper on AlphaCodium, -
Llama 3 8B and 70B Now Available on Poe
By
–
Both Llama 3 8B and 70B are available at https://
poe.com/Llama-3-8B-T and https://
poe.com/Llama-3-70B-T and across all Poe apps. (2/2) -
Llama 3 70B Now Available on Poe Platform
By
–
Llama 3 is now available on Poe! Llama 3 70B is now the most powerful open source model available, with state-of-the-art performance across industry benchmarks. It delivers new capabilities like enhanced reasoning, better code generation, and improved instruction following. (1/2)
-
Meta’s Llama 3 Congratulations and AI Progress Recognition
By
–
@AIatMeta is one of the best things ever happened to AI progress. Congrats on llama 3! https://
ai.meta.com/blog/meta-llam
a-3/
… -
LangChain AWS Integration Launches Bedrock Chat Models
By
–
`langchain-aws` integration package We're really excited to partner with Amazon Web Services @awscloud in the launch of our latest partner package. You can now access Bedrock chat models from @AnthropicAI
, @MistralAI
, @Cohere
, @AI21Labs
, your custom SageMaker models, -
Chinchilla Scaling Laws: Compute Optimality vs Convergence Point
By
–
no. people misunderstand chinchilla.
chinchilla doesn't tell you the point of convergence.
it tells you the point of compute optimality.
if all you care about is perplexity, for every FLOPs compute budget, how big model on how many tokens should you train?
for reasons not fully