[GH-ISSUE #1112] Support ollama create with PyTorch #26319

Closed
opened 2026-04-22 02:31:15 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @jmorganca on GitHub (Nov 13, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1112

Currently, create a model via a Modelfile supports importing GGUF format model binaries. Ollama should also support importing PyTorch models directly via ollama create

Related:

Originally created by @jmorganca on GitHub (Nov 13, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1112 Currently, create a model via a `Modelfile` supports importing GGUF format model binaries. Ollama should also support importing PyTorch models directly via `ollama create` Related: * https://github.com/jmorganca/ollama/issues/1037 * https://github.com/jmorganca/ollama/issues/1097
GiteaMirror added the feature request label 2026-04-22 02:31:15 -05:00
Author
Owner

@jmorganca commented on GitHub (May 6, 2024):

This is largely fixed for the model architectures supported by ollama create (e.g. mistral)

<!-- gh-comment-id:2097089149 --> @jmorganca commented on GitHub (May 6, 2024): This is largely fixed for the model architectures supported by `ollama create` (e.g. mistral)
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#26319