[GH-ISSUE #4052] Unable to create gguf file for my finetuned mixtral8x7b model #49026

Closed
opened 2026-04-28 10:37:02 -05:00 by GiteaMirror · 6 comments
Owner

Originally created by @Nimmalapudi-Pratyusha on GitHub (Apr 30, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4052

What is the issue?

I am trying to create a gguf file for my finetuned mixtral model but it keeps throwing following error:

Command : python llm/llama.cpp/convert.py /home/raft_mixtral_2epochs_v1 --outtype q8_0 --outfile converted.bin
Error:

raise FileNotFoundError(f"Can't find model in directory {path}")
FileNotFoundError: Can't find model in directory /home/raft_mixtral_2epochs_v1


Below are the content's of my raft_mixtral_2epochs_v1 folder :
Screenshot from 2024-04-30 19-01-05

OS

No response

GPU

No response

CPU

No response

Ollama version

0.1.32

Originally created by @Nimmalapudi-Pratyusha on GitHub (Apr 30, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4052 ### What is the issue? I am trying to create a gguf file for my finetuned mixtral model but it keeps throwing following error: Command :` python llm/llama.cpp/convert.py /home/raft_mixtral_2epochs_v1 --outtype q8_0 --outfile converted.bin` Error: ``` raise FileNotFoundError(f"Can't find model in directory {path}") FileNotFoundError: Can't find model in directory /home/raft_mixtral_2epochs_v1 ``` Below are the content's of my raft_mixtral_2epochs_v1 folder : ![Screenshot from 2024-04-30 19-01-05](https://github.com/ollama/ollama/assets/129523872/fff3327a-5e96-4991-8ecb-c2fc0c539f32) ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-04-28 10:37:02 -05:00
Author
Owner

@thinkverse commented on GitHub (Apr 30, 2024):

Have you tried convert-hf-to-gguf-update.py1 instead of convert.py to see if that works?

<!-- gh-comment-id:2085414443 --> @thinkverse commented on GitHub (Apr 30, 2024): Have you tried `convert-hf-to-gguf-update.py`[^1] instead of `convert.py` to see if that works? [^1]: https://github.com/ollama/ollama/blob/main/docs/import.md#convert-the-model
Author
Owner

@Nimmalapudi-Pratyusha commented on GitHub (Apr 30, 2024):

Have you tried convert-hf-to-gguf-update.py1 instead of convert.py to see if that works?

Footnotes

  1. https://github.com/ollama/ollama/blob/main/docs/import.md#convert-the-model

It's throwing below error when I tried with convert-hf-to-gguf-update.py
Command : python llama.cpp/convert-hf-to-gguf-update.py <hftoken> /home/raft_mixtral_2epochs_v1 --outfile raft_v1.gguf --outtype q8_0
error:
Usage: python convert-hf-to-gguf-update.py <huggingface_token>.

<!-- gh-comment-id:2085457572 --> @Nimmalapudi-Pratyusha commented on GitHub (Apr 30, 2024): > Have you tried `convert-hf-to-gguf-update.py`[1](#user-content-fn-1-3ce43143dc53c24086b5538bdf8feba4) instead of `convert.py` to see if that works? > > ## Footnotes > 1. https://github.com/ollama/ollama/blob/main/docs/import.md#convert-the-model [↩](#user-content-fnref-1-3ce43143dc53c24086b5538bdf8feba4) It's throwing below error when I tried with `convert-hf-to-gguf-update.py` Command : `python llama.cpp/convert-hf-to-gguf-update.py <hftoken> /home/raft_mixtral_2epochs_v1 --outfile raft_v1.gguf --outtype q8_0` error: Usage: python convert-hf-to-gguf-update.py <huggingface_token>.
Author
Owner

@pdevine commented on GitHub (Apr 30, 2024):

@Nimmalapudi-Pratyusha I think you're just specifying the wrong file path for the file.

<!-- gh-comment-id:2086661200 --> @pdevine commented on GitHub (Apr 30, 2024): @Nimmalapudi-Pratyusha I think you're just specifying the wrong file path for the file.
Author
Owner

@pdevine commented on GitHub (May 3, 2024):

@Nimmalapudi-Pratyusha did you manage to get this to work?

<!-- gh-comment-id:2093399631 --> @pdevine commented on GitHub (May 3, 2024): @Nimmalapudi-Pratyusha did you manage to get this to work?
Author
Owner

@Nimmalapudi-Pratyusha commented on GitHub (May 7, 2024):

The issue wasn't with the path, I found the fix here -
https://github.com/ggerganov/llama.cpp/issues/4199
Screenshot from 2024-05-07 14-03-14

<!-- gh-comment-id:2097747802 --> @Nimmalapudi-Pratyusha commented on GitHub (May 7, 2024): The issue wasn't with the path, I found the fix here - https://github.com/ggerganov/llama.cpp/issues/4199 ![Screenshot from 2024-05-07 14-03-14](https://github.com/ollama/ollama/assets/129523872/057b7cca-8916-47e9-86fd-eb01130f2d8a)
Author
Owner

@pdevine commented on GitHub (May 7, 2024):

Glad you got it working!

<!-- gh-comment-id:2098949488 --> @pdevine commented on GitHub (May 7, 2024): Glad you got it working!
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#49026