[GH-ISSUE #6426] convert: vocab conversion incorrect #4041

Closed
opened 2026-04-12 14:55:59 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @jmorganca on GitHub (Aug 19, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6426

Originally assigned to: @mxyng on GitHub.

What is the issue?

To reproduce, clone https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct then create a Modelfile:

FROM .

Lastly, create a model:

ollama create test

When trying to run the model, an assertion will be fired:

Error: llama runner process has terminated: GGML_ASSERT(vocab.id_to_token.size() == vocab.token_to_id.size()) failed

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @jmorganca on GitHub (Aug 19, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6426 Originally assigned to: @mxyng on GitHub. ### What is the issue? To reproduce, clone https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct then create a `Modelfile`: ``` FROM . ``` Lastly, create a model: ``` ollama create test ``` When trying to run the model, an assertion will be fired: ``` Error: llama runner process has terminated: GGML_ASSERT(vocab.id_to_token.size() == vocab.token_to_id.size()) failed ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 14:55:59 -05:00
Author
Owner

@jmorganca commented on GitHub (Aug 20, 2024):

Also happens with https://huggingface.co/ibm-granite/granite-3b-code-instruct-128k

<!-- gh-comment-id:2299309773 --> @jmorganca commented on GitHub (Aug 20, 2024): Also happens with https://huggingface.co/ibm-granite/granite-3b-code-instruct-128k
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#4041