RedPajama-INCITE-7B-Base-sharded-bf16
This is the togethercomputer/RedPajama-INCITE-7B-Base model, but the model file(s) have been sharded to ~2GB each to ensure it can be loaded on low-RAM runtimes (like Colab).
Please refer to the original model card for all details/issues w.r.t. to this model. - inference examples are also available on the original model card linked above. - example colab notebook covering the basics
- Downloads last month
- 11
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.