The LLM Playground: March 2024 release and Product Hunt launch

We are excited to announce the March 2024 LLM Playground release. This update includes Inference Metrics with i/o token counts, throughput, and inference cost and Persisted Sessions, where you can review and resume previous chat sessions.

New features

The Airtrain LLM Playground now features:

• Simultaneous prompting of multiple models 
• 18 LLMs supported (8 open-source, 10 proprietary)
• New! Inference Metrics: input/output token counts, throughput, and inference cost
• New! Persisted Sessions: review and resume previous chat sessions

Supported models

• Anthropic Claude 3 (Opus, Sonnet), Claude 2.1, Claude 1.2
• Mistral Large, Medium, Small, 7B, and Mixtral
• OpenAI GPT-4 and GPT-3.5 Turbo
• Google Gemini Pro and Gemma 2B, 7B
• Meta Llama 2 7B, 13B, 70B
• Microsoft Phi-2

Support us on Product Hunt

In conjunction with this new feature release, we are also launching the LLM Playground on Product Hunt. Here is how you can help:

• Sign up on our Product Hunt page to get notified when it goes live.
• Support us: We would greatly appreciate an upvote on Product Hunt. Also, feel free to leave a comment or ask any questions you may have on our page. Product feedback will help increase our visibility.
• Share the LLM Playground: Like it? Love it? Share the love – and our Product Hunt page –  with your networks using the hashtag #LLMVibeCheck.

For assistance or additional information, you are invited to join our community Slack or to read the documentation.

As always, please let us know if you have any thoughts or ideas on how we can improve the LLM Playground experience. Thank you!