[GH-ISSUE #7864] Please sync with llama.cpp for the update of bert_base like models. #51542

Closed
opened 2026-04-28 20:30:14 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @BeNhNp on GitHub (Nov 27, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7864

What is the issue?

currently ollama_llama_server can't return properly with google bert_base models, while llama.cpp have already supported, I've varified with transformers.

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @BeNhNp on GitHub (Nov 27, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7864 ### What is the issue? currently [ollama_llama_server](https://github.com/ollama/ollama/blob/main/llm/server.go#L894) can't return properly with google bert_base models, while llama.cpp have already supported, I've varified with `transformers`. ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-28 20:30:14 -05:00
Author
Owner

@dhiltgen commented on GitHub (Jul 4, 2025):

I think we can close this out - we've updated llama.cpp since then.

<!-- gh-comment-id:3037218355 --> @dhiltgen commented on GitHub (Jul 4, 2025): I think we can close this out - we've updated llama.cpp since then.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#51542