[GH-ISSUE #1285] Support GPT2LMHeadModel architecture #661

Closed
opened 2026-04-12 10:21:04 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @jhagelback on GitHub (Nov 27, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1285

Any plans on supporting GPT2LMHeadModel architecture?

Originally created by @jhagelback on GitHub (Nov 27, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1285 Any plans on supporting _GPT2LMHeadModel_ architecture?
GiteaMirror added the feature requestmodel labels 2026-04-12 10:21:04 -05:00
Author
Owner

@jmorganca commented on GitHub (Dec 23, 2024):

This should be supported now – you can import it (via an existing GGUF file). Let me know if you hit any issues 😊

<!-- gh-comment-id:2558827821 --> @jmorganca commented on GitHub (Dec 23, 2024): This should be supported now – you can [import it](https://github.com/ollama/ollama/blob/main/docs/import.md) (via an existing GGUF file). Let me know if you hit any issues 😊
Author
Owner

@echostorm commented on GitHub (Feb 8, 2025):

I tried importing a GPT2LMHeadModel architecture based model and I faced same issue [unknown architecture]

<!-- gh-comment-id:2645981251 --> @echostorm commented on GitHub (Feb 8, 2025): I tried importing a GPT2LMHeadModel architecture based model and I faced same issue [unknown architecture]
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#661