github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1448] Pytorch model quantization, using ollama/quantize docker is not working. #47287

New Issue
Closed
opened 2026-04-28 03:30:37 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 03:30:37 -05:00
Owner
Copy Link

Originally created by @phalexo on GitHub (Dec 9, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1448

(base) alexo@GrayMatters:/opt/data/data/Salesforce/codegen25-7b-mono$ docker run --rm -v .:/model -v .:/workdir ollama/quantize -q q6_K ./
sh: 0: cannot open entrypoint.sh: No such file

Originally created by @phalexo on GitHub (Dec 9, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1448 (base) alexo@GrayMatters:/opt/data/data/Salesforce/codegen25-7b-mono$ docker run --rm -v .:/model -v .:/workdir ollama/quantize -q q6_K ./ sh: 0: cannot open entrypoint.sh: No such file
GiteaMirror commented 2026-04-28 03:30:38 -05:00
Author
Owner
Copy Link

@netroy commented on GitHub (Feb 12, 2024):

Looking at the docker image ollama/quantize, /workdir seems to be the WORKDIR, where llama.cpp is cloned and compiled, and where the entrypoint.sh is copied over to.
So, when you do -v .:/workdir, all those files are gone from the container.
You could try to either not mount a volume to that path, or first copy over the content of that folder from the image into the current folder.

<!-- gh-comment-id:1938434964 --> @netroy commented on GitHub (Feb 12, 2024): Looking at the docker image `ollama/quantize`, `/workdir` seems to be the `WORKDIR`, where llama.cpp is cloned and compiled, and where the `entrypoint.sh` is copied over to. So, when you do `-v .:/workdir`, all those files are gone from the container. You could try to either not mount a volume to that path, or first copy over the content of that folder from the image into the current folder.
GiteaMirror commented 2026-04-28 03:30:39 -05:00
Author
Owner
Copy Link

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

Hi there, we've updated the docs to use python and llama.cpp's quantize utility directly – let me know if this helps

<!-- gh-comment-id:1953342939 --> @jmorganca commented on GitHub (Feb 20, 2024): Hi there, we've updated the [docs](https://github.com/ollama/ollama/blob/main/docs/import.md) to use `python` and llama.cpp's `quantize` utility directly – let me know if this helps
GiteaMirror commented 2026-04-28 03:30:39 -05:00
Author
Owner
Copy Link

@netroy commented on GitHub (Feb 21, 2024):

@jmorganca Does this mean that I should close #2461 ?

<!-- gh-comment-id:1956442304 --> @netroy commented on GitHub (Feb 21, 2024): @jmorganca Does this mean that I should close #2461 ?
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
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#47287
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?