TweetSyncdocs

ReplicateAI

Setting Up the API Key for ReplicateAI:

1. Create an account on ReplicateAI.
2. Once logged in, go to your account settings.
3. Look for the "API Key" option and generate a new key.
4. Copy the generated API key.

Recommended Models

1. meta/meta-llama-3-70b-instruct

   • A 70 billion parameter language model fine-tuned for chat completions.

2. meta/meta-llama-3-8b

   • An 8 billion parameter base version of Llama 3.

3. meta/meta-llama-3-8b-instruct

   • An 8 billion parameter language model fine-tuned for chat completions.

4. mistralai/mixtral-8x7b-instruct-v0.1

   • A generative Sparse Mixture of Experts tuned for assistance.

5. meta/llama-2-7b-chat

   • A 7 billion parameter language model fine-tuned for chat completions.

6. meta/llama-2-70b-chat

   • A 70 billion parameter language model fine-tuned for chat completions.

7. meta/llama-2-13b-chat

   • A 13 billion parameter language model fine-tuned for chat completions.

8. mistralai/mistral-7b-instruct-v0.2

   • An improved instruct fine-tuned version of Mistral-7B.

9. mistralai/mistral-7b-v0.1

   • A 7 billion parameter language model from Mistral.

10. mistralai/mistral-7b-instruct-v0.1

    • An instruction-tuned 7 billion parameter language model.

11. replicate/dolly-v2-12b

    • An open-source instruction-tuned large language model by Databricks.

12. meta/meta-llama-3-70b

    • A 70 billion parameter base version of Llama 3.

13. 01-ai/yi-34b-chat

    • A large language model trained from scratch by 01.AI.

14. replicate/vicuna-13b

    • A large language model fine-tuned on ChatGPT interactions.

15. 01-ai/yi-6b

    • A large language model trained from scratch by 01.AI.

16. replicate/flan-t5-xl

    • A language model by Google for tasks like classification and summarization.

17. stability-ai/stablelm-tuned-alpha-7b

    • A 7 billion parameter language model by Stability AI.

18. replicate/llama-7b

    • A Transformers implementation of the LLaMA language model.

19. google-deepmind/gemma-2b-it

    • A 2 billion parameter instruct version of Google’s Gemma model.

20. google-deepmind/gemma-7b-it

    • A 7 billion parameter instruct version of Google’s Gemma model.

21. nateraw/nous-hermes-2-solar-10.7b

    • The Nous Hermes 2 - SOLAR 10.7B model.

22. replicate/oasst-sft-1-pythia-12b

    • An open-source instruction-tuned large language model by Open-Assistant.

23. kcaverly/nous-hermes-2-yi-34b-gguf

    • A state-of-the-art Yi fine-tune on GPT-4 generated synthetic data.

24. replicate/gpt-j-6b

    • A large language model by EleutherAI.

25. nateraw/nous-hermes-llama2-awq

    • Served with vLLM, by TheBloke.

26. google-deepmind/gemma-7b

    • A 7 billion parameter base version of Google’s Gemma model.

27. 01-ai/yi-6b-chat

    • A large language model trained from scratch by 01.AI.

28. lucataco/qwen1.5-72b

    • A beta version of Qwen2, a transformer-based model.

29. lucataco/phi-2

    • A model by Microsoft.

30. replit/replit-code-v1-3b

    • A code generation model by Replit.

31. google-deepmind/gemma-2b

    • A 2 billion parameter base version of Google’s Gemma model.

32. lucataco/qwen1.5-14b

    • A beta version of Qwen2, a transformer-based model.

33. adirik/mamba-2.8b

    • A 2.8 billion parameter state space language model.

34. lucataco/phixtral-2x2_8

    • A MoE model with two Microsoft/phi-2 models.

35. lucataco/qwen1.5-7b

    • A beta version of Qwen2, a transformer-based model.

36. adirik/mamba-130m

    • A 130 million parameter state space language model.

37. lucataco/olmo-7b

    • An Open Language Model series for language model science.

38. adirik/mamba-1.4b

    • A 1.4 billion parameter state space language model.

39. adirik/mamba-2.8b-slimpj

    • A 2.8 billion parameter state space language model.

40. adirik/mamba-370m

    • A 370 million parameter state space language model.

41. adirik/mamba-790m

    • A 790 million parameter state space language model.