github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 12:48:05 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #4830] model import to Ollama #3053

New Issue
Closed
opened 2026-04-12 13:29:09 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 13:29:09 -05:00
Owner
Copy Link

Originally created by @fingerfree77 on GitHub (Jun 5, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4830

Is it possible to import model to Ollama from HuggingFace which is not listed in the script convert-hf-to-gguf.py?
In my case model: https://huggingface.co/ai-forever/ruGPT-3.5-13B
When I try import got error:

Traceback (most recent call last):
  File "llm/llama.cpp/convert-hf-to-gguf.py", line 2865, in <module>
    main()
  File "llm/llama.cpp/convert-hf-to-gguf.py", line 2850, in main
    model_instance.set_vocab()
  File "llm/llama.cpp/convert-hf-to-gguf.py", line 114, in set_vocab
    self._set_vocab_gpt2()
  File "llm/llama.cpp/convert-hf-to-gguf.py", line 500, in _set_vocab_gpt2
    tokens, toktypes, tokpre = self.get_vocab_base()
  File "llm/llama.cpp/convert-hf-to-gguf.py", line 379, in get_vocab_base
    tokpre = self.get_vocab_base_pre(tokenizer)
  File "llm/llama.cpp/convert-hf-to-gguf.py", line 491, in get_vocab_base_pre
    raise NotImplementedError("BPE pre-tokenizer was not recognized - update get_vocab_base_pre()")
NotImplementedError: BPE pre-tokenizer was not recognized - update get_vocab_base_pre()
Originally created by @fingerfree77 on GitHub (Jun 5, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4830 Is it possible to import model to Ollama from HuggingFace which is not listed in the script convert-hf-to-gguf.py? In my case model: https://huggingface.co/ai-forever/ruGPT-3.5-13B When I try import got error: ``` Traceback (most recent call last): File "llm/llama.cpp/convert-hf-to-gguf.py", line 2865, in <module> main() File "llm/llama.cpp/convert-hf-to-gguf.py", line 2850, in main model_instance.set_vocab() File "llm/llama.cpp/convert-hf-to-gguf.py", line 114, in set_vocab self._set_vocab_gpt2() File "llm/llama.cpp/convert-hf-to-gguf.py", line 500, in _set_vocab_gpt2 tokens, toktypes, tokpre = self.get_vocab_base() File "llm/llama.cpp/convert-hf-to-gguf.py", line 379, in get_vocab_base tokpre = self.get_vocab_base_pre(tokenizer) File "llm/llama.cpp/convert-hf-to-gguf.py", line 491, in get_vocab_base_pre raise NotImplementedError("BPE pre-tokenizer was not recognized - update get_vocab_base_pre()") NotImplementedError: BPE pre-tokenizer was not recognized - update get_vocab_base_pre() ```
GiteaMirror added the model label 2026-04-12 13:29:09 -05:00
GiteaMirror commented 2026-04-12 13:29:11 -05:00
Author
Owner
Copy Link

@sealad886 commented on GitHub (Jun 11, 2024):

The short answer is no. Ollama relies on the llama.cpp backend to serve the API. Open up an enhancement request on the llama.cpp project, or (even better!) see if you can add the pre-tokenizer yourself and open up a pull request!

<!-- gh-comment-id:2159734739 --> @sealad886 commented on GitHub (Jun 11, 2024): The short answer is no. Ollama relies on the llama.cpp backend to serve the API. Open up an [enhancement request](https://github.com/ggerganov/llama.cpp/issues/new/choose) on the llama.cpp project, or (even better!) see if you can add the pre-tokenizer yourself and open up a pull request!
GiteaMirror commented 2026-04-12 13:29:11 -05:00
Author
Owner
Copy Link

@DewiarQR commented on GitHub (Aug 12, 2024):

I would like to know if there has already been any progress in this direction?

<!-- gh-comment-id:2283634149 --> @DewiarQR commented on GitHub (Aug 12, 2024): I would like to know if there has already been any progress in this direction?
GiteaMirror commented 2026-04-12 13:29:13 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Sep 4, 2024):

Closing for https://github.com/ollama/ollama/issues/1285 – thanks for the issue!

<!-- gh-comment-id:2329064324 --> @jmorganca commented on GitHub (Sep 4, 2024): Closing for https://github.com/ollama/ollama/issues/1285 – thanks for the issue!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label model
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#3053
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?