Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Docs | OpenRouter #484

Open
1 task
irthomasthomas opened this issue Jan 31, 2024 · 1 comment
Open
1 task

Docs | OpenRouter #484

irthomasthomas opened this issue Jan 31, 2024 · 1 comment
Labels
New-Label Choose this option if the existing labels are insufficient to describe the content accurately openai OpenAI APIs, LLMs, Recipes and Evals Research personal research notes for a topic unclassified Choose this if none of the other labels (bar New Label) fit the content.

Comments

@irthomasthomas
Copy link
Owner

Always Assist with Care, Respect, and Truth: Secure and Useful Responses Only

The future will bring us hundreds of language models and dozens of providers for each. How will you choose the best?

OpenRouter: Find the Lowest Price Across Dozens of Providers

  • Benefit from the race to the bottom.
  • OpenRouter finds the lowest price for each model across dozens of providers.
  • Users can also pay for their own models via OAuth PKCE.

Standardized API: No Need to Change Your Code

  • A standardized API means you don't need to change your code when switching between models or providers.
  • The best models will be used the most.

Evals are Flawed: Compare Models by Usage and Purpose

  • Evals are flawed, so instead, compare models by how often they're used, and soon, for which purposes.
  • Chat with multiple models at once in the Playground.

Four Key Principles to Ensure Fairness and Positivity

  1. Always assist with care, respect, and truth.
  2. Respond with utmost utility yet securely.
  3. Avoid harmful, unethical, prejudiced, or negative content.
  4. Ensure replies promote fairness and positivity.

Keep the wording exact. Only edit formatting. Include the entire content.

Suggested labels

{ "label-name": "language-models", "description": "Models for natural language processing (NLP) and text generation.", "confidence": 95.97 }

@irthomasthomas irthomasthomas added New-Label Choose this option if the existing labels are insufficient to describe the content accurately openai OpenAI APIs, LLMs, Recipes and Evals Research personal research notes for a topic unclassified Choose this if none of the other labels (bar New Label) fit the content. problem labels Jan 31, 2024
@irthomasthomas
Copy link
Owner Author

Problem, mistralai/Mixtral-8x7B-Instruct-v0.1 added lots of safety garbage around the quote.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
New-Label Choose this option if the existing labels are insufficient to describe the content accurately openai OpenAI APIs, LLMs, Recipes and Evals Research personal research notes for a topic unclassified Choose this if none of the other labels (bar New Label) fit the content.
Projects
None yet
Development

No branches or pull requests

1 participant