Closed steventkrawczyk closed 10 months ago
We have integrated with Replicate. You can run various models, such as Llama 2 and Stable Diffusion.
If any model doesn't work with our ReplicateExperiment
, please feel free to comment here or open another issue.
🚀 The feature
Replicate supports serverless inference for LLMs: https://replicate.com/collections/language-models
We should create a replicate experiment.
Motivation, pitch
Easy way to test OSS LLMs, good to compare to Huggingface hosted endpoints
Alternatives
No response
Additional context
No response