Open source AI models are full of surprises
@replicate
-
Dragon Detection AI Model Now Available on Replicate
By
–
A lot of you are asking us, "If only I could I detect dragons in my photographs using AI" Well now you can, thanks to community member @hadilq
's dragon-notdragon Try it today on Replicate! https://
replicate.com/hadilq/dragon-
notdragon
… -
Replicate AI Models Now Available Directly in Photoshop
By
–
Use Replicate models right in Photoshop! So cool https://t.co/JByhKjapMF
— Replicate (@replicate) 6 mai 2024Use Replicate models right in Photoshop! So cool
-
Snowflake Arctic: Massive Open-Source Model for SQL and Coding
By
–
Snowflake Arctic is a new open-source language model from @SnowflakeDB
. – It's absolutely massive (480B)
– It's very good at SQL and other coding tasks
– It cost just under $2M to train (less than half of Llama) Try it out: https://
arctic.streamlit.app -
Test Llama 3 with Full API Playground and Documentation
By
–
Or try the full API playground, where you can test Llama 3 in detail and get all the documentation you need: https://
replicate.com/meta/meta-llam
a-3-70b-instruct
… -
Use Llama 3 API on Replicate with Copy-Paste Code
By
–
You can use Llama 3 with an API on Replicate. Check out our blog post, where we give you the exact code you need to copy-paste to add it to your app
-
Llama 3: Developer-Friendly Models for Various AI Tasks
By
–
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
-
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