Llama 2 is the first open-source language model of the same caliber as OpenAI's models. You can run it on Replicate using JavaScript, Python, cURL, Go, Swift, or any other language. Here's a guide to get you started running Llama 2 with an API.
@replicate
-
Next.js Template for SDXL App Launch
By
–
We made a @nextjs template for getting an SDXL app up and running in seconds. https://
github.com/replicate/gett
ing-started-nextjs
… -
Llama 2 Now Runs 2x Faster on Replicate
By
–
We added some creatine to our feed, and Llama 2 on Replicate now runs 2x faster. https://t.co/JEU8a7HYmw pic.twitter.com/HOi0yF83pC
— Replicate (@replicate) 26 juillet 2023We added some creatine to our feed, and Llama 2 on Replicate now runs 2x faster. https://
replicate.com/replicate/llam
a70b-v2-chat
… -
Replicate Models Now Available on NVIDIA A40 GPUs
By
–
You can now run Replicate models on @nvidia
's A40 GPUs. For many models, A40s can be 80-90% as fast as A100s but much cheaper. -
Run Llama 2 Locally on Your Computer Mac or Phone
By
–
One of the coolest things about Llama 2 is that you can run it on your own computer, your M1/M2 Mac, or even on your phone. Follow our guide to learn how:
-
Llama 2 70B Updated with System Prompt Control
By
–
Ahoy mateys! We've updated Llama 2 70B to expose the system_prompt, giving you more control over the output. https://
replicate.com/p/tyjeiltbkqsi
rmlxvwvdr4bpsy
…
