This holiday season, use Perplexity to look up recipes, settle debates with family, and plan parties. Dive deeper with Copilot, visualize answers with image and videos, and more. THANKS23 expires at Dec 3 11:59pm and grants $40 off annual plans. New/returning subscribers only.
@perplexity_ai
-
NVIDIA H100 Optimizes Llama 2 70B Inference Performance
By
–
Discover how @nvidia H100 enhances Llama 2 70B performance in our latest blog. Learn more about how we optimize AI inference latency and throughput here: https://
pplx.ai/sJdwcuK -
Perplexity AI launches multimodal search with images and videos
By
–
Your quest for knowledge expands beyond text. Our latest update brings a new dimension to your search, seamlessly integrating images and videos to visually enhance every answer. Try it now on http://
pplx.ai! -
Perplexity releases higher performance AI models, now hiring
By
–
Evaluation prompts were taken from @AnthropicAI hh-rlhf dataset. What’s next? We’ll be releasing more models with higher performance in the future. Stay tuned! P.S,
We're hiring! https://
blog.perplexity.ai/careers -
Perplexity 70B Outperforms Llama on Refusal Rates
By
–
Our models prioritize intelligence, usefulness, and versatility on an array of tasks, without imposing moral judgments or limitations. Comparing pplx-70b-chat and llama-2-70b-chat (by @AIatMeta ), human evaluators saw: 22.7% fewer “full denials” and 31.9% more “no denials”
-
Perplexity Launches pplx-7b and pplx-70b Chat Models
By
–
We’re excited to announce two models we’ve been training in-house: pplx-7b-chat and pplx-70b-chat! Both these models are built on top of open-source LLMs and fine-tuned for chat. They are available as an alpha release, via Labs and pplx-api. Try it out: https://t.co/2yYQB9jln7 pic.twitter.com/pNxHEWsyjp
— Perplexity (@perplexity_ai) 27 octobre 2023We’re excited to announce two models we’ve been training in-house: pplx-7b-chat and pplx-70b-chat! Both these models are built on top of open-source LLMs and fine-tuned for chat. They are available as an alpha release, via Labs and pplx-api. Try it out: http://
labs.pplx.ai -
Replit Code LLM Integration in Perplexity API
By
–
It was a pleasure working with @replit to integrate their most advanced code LLM replit-code-v1.5-3b to our API. Try it out through our pplx-api (https://t.co/SP03AxN18R) pic.twitter.com/6TZVFKbXDe
— Perplexity (@perplexity_ai) 10 octobre 2023It was a pleasure working with @replit to integrate their most advanced code LLM replit-code-v1.5-3b to our API. Try it out through our pplx-api (
http://
labs.pplx.ai/docs) -
AWS Inception Program Partnership for Startup Founders
By
–
We’ve been working with @AWSstartups as a founding member of the #inception program.
-
Open-source LLM API enables fast inference without GPU requirements
By
–
Ideal for developers seeking to incorporate open-source LLMs into their products, our API offers fast inference speeds without requiring extensive C++/CUDA knowledge or GPU access. Subscribe to Perplexity Pro to try it out: http://
pplx.ai/pro -
Fast REST API for Open-Source LLMs with Lower Latency
By
–
Key features: • Easy-to-use REST API • Up to 2.9x lower latency than Replicate & 3.1x lower than Anyscale • Reliable, battle-tested infra, serving 1B tokens in our prod environment daily • One stop shop for open-source LLMs Read the API specs: