Llama 3 is made for developers. It's permissively licensed and it comes in useful sizes. Use Llama 3 70B models for dialogue, instruction following, code generation, reasoning. Or Llama 3 8B models for summarization, translation and other cases where efficiency is everything
GENERATIVE AI
-
Llama 3 Models Now Available for Chat on Replicate
By
–
Llama 3 models include base and instruction-tuned models. You can chat with the instruct models right now at llama3 dot replicate dot dev http://
llama3.replicate.dev lll -
Meta Llama 3 Language Model Released on Replicate
By
–
Meta Llama 3 is out now and available on Replicate. This language model family comes in 8B and 70B parameter sizes, with context windows of 8K tokens. The models beat most other open source models on industry benchmarks and are licensed for commercial use. Try them here
-
Multimodal AI capabilities more limited than apparent
By
–
Multimodal capabilities are more limited than it seems at first. Lots of guessing
-
Clarifying AI Autonomy in Creative Automation and Innovation
By
–
To be clear, it doesn’t do these things autonomously (some comments seemed confused) On innovation: https://
oneusefulthing.org/p/automating-c
reativity
… -
Texting girlfriend about llama day AI model
By
–
Texting my gf, who is as outside of tech as can be, about llama day
-
Meta Llama 3 Release: Walking into NYC Meta Offices
By
–
About to walk into the Meta offices in NYC. Guess I should shake everyone’s hand for this release. https://
ai.meta.com/blog/meta-llam
a-3/
… -
Meta’s Instruct and Non-Instruct Models Available on Replicate
By
–
How do you mean? Replicate have both the instruct and the non-instruct models linked here: https://
replicate.com/meta -
Editorial Strategy: Avoiding Competition with Specialized AI Coverage
By
–
Decided long ago when I launched to do my best to not spend my energy competing with places with way more resources or more specialized than myself so will let the experts do the teardowns and the Important Places get all the interviews. Tomorrow’s issue isn’t about llama 3 .
-
Finetune Both Variants Using AutoTrain
By
–
You can finetune both variants using AutoTrain: http://
hf.co/autotrain