[GH-ISSUE #3767] The template that is suggested for Llama 3 does not appear to work correctly. #2325

Closed
opened 2026-04-12 12:38:48 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @phalexo on GitHub (Apr 19, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3767

What is the issue?

I am trying to convert a model file with ollama.

The resulting model 1) Insert "assitant" into text inappropriately and 2) seems to just run and run without stopping.

What is the correct template for Llama 2 8B model?

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

No response

Originally created by @phalexo on GitHub (Apr 19, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3767 ### What is the issue? I am trying to convert a model file with ollama. The resulting model 1) Insert "assitant" into text inappropriately and 2) seems to just run and run without stopping. What is the correct template for Llama 2 8B model? ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 12:38:48 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2325