github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7914] how to use Modefile build customer model when gguf file have sevral sub files? #5065

New Issue
Closed
opened 2026-04-12 16:09:33 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 16:09:33 -05:00
Owner
Copy Link

Originally created by @cqray1990 on GitHub (Dec 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7914

What is the issue?

like this: qwen2.5-instruct-0001.gguf
qwen2.5-instruct-0002.gguf

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @cqray1990 on GitHub (Dec 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7914 ### What is the issue? like this: qwen2.5-instruct-0001.gguf qwen2.5-instruct-0002.gguf ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 16:09:33 -05:00
GiteaMirror commented 2026-04-12 16:09:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 3, 2024):

Merge them into a single file. There are serveral projects on github that have a program to do that.

If you have docker installed, it's quite convenient to pull the llama.cpp docker image (warning, 4GB): docker pull ghcr.io/ggerganov/llama.cpp:full. It has a bunch of tools for dealing with GGUF files (splitting, merging, quantizing, etc)

$ mv qwen2.5-instruct-0001.gguf qwen2.5-instruct-00001-of-00002.gguf
$ mv qwen2.5-instruct-0002.gguf qwen2.5-instruct-00002-of-00002.gguf
$ docker run --rm -it -v .:/workdir --workdir /workdir --entrypoint /app/llama-gguf-split ghcr.io/ggerganov/llama.cpp:full --merge qwen2.5-instruct-00001-of-00002.gguf qwen2.5-instruct.gguf
<!-- gh-comment-id:2514348036 --> @rick-github commented on GitHub (Dec 3, 2024): Merge them into a single file. There are serveral projects on github that have a program to do that. If you have docker installed, it's quite convenient to pull the [llama.cpp](https://github.com/ggerganov/llama.cpp) docker image (warning, 4GB): `docker pull ghcr.io/ggerganov/llama.cpp:full`. It has a bunch of tools for dealing with GGUF files (splitting, merging, quantizing, etc) ```console $ mv qwen2.5-instruct-0001.gguf qwen2.5-instruct-00001-of-00002.gguf $ mv qwen2.5-instruct-0002.gguf qwen2.5-instruct-00002-of-00002.gguf $ docker run --rm -it -v .:/workdir --workdir /workdir --entrypoint /app/llama-gguf-split ghcr.io/ggerganov/llama.cpp:full --merge qwen2.5-instruct-00001-of-00002.gguf qwen2.5-instruct.gguf ```
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 bug
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#5065
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?