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 #2207] Magicoder-S-DS-6.7B-GGUF is not working #1262

New Issue
Closed
opened 2026-04-12 11:03:27 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 11:03:27 -05:00
Owner
Copy Link

Originally created by @pablovalle on GitHub (Jan 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2207

Hi,

I wanted to run a specific version of magicoder (Magicoder-S-DS-6.7B-GGUF) so I started creating a customize Modelfile as follows:

FROM ./magicoder-s-ds-6.7b
TEMPLATE """{{- if .System }}
<|im_start|>system {{ .System }}<|im_end|>
{{- end }}
<im start|>user
{{ .Prompt }}<|im_end|>
<|im start|>assistant
"""
PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"

Then I ran the following command:

ollama create pruebaPablo -f ./Modelfile

Everyting worked properly with the following output:

transferring model data
creating model layer
creating template layer
creating system layer
creating parameters layer
creating config layer
using already created layer sha256:7f0011bbe58c5bd2b3aa81abaa595d0e2181d7fa287a39a5899e7bb9a3117262
writing layer sha256:fbd3a46e44915917bdfe24b8c1cb7bf74f49cf12761b45c9787842b477c5a8fe
using already created layer sha256:f02dd72bb2423204352eabc5637b44d79d17f109fdb510a7c51455892aa2d216
writing layer sha256:f37e567548df4ecb18a3ef059c296cc50f0e0a11e5c1eb04b427688b1d4ea3ea
writing manifest
success

But, then, when I execute the run instruction it gets stuck loading and I can not send anything to the model as you can see in the following image:

image

Is there anything I am doing wrong?

Many thanks,
Pablo.

Originally created by @pablovalle on GitHub (Jan 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2207 Hi, I wanted to run a specific version of magicoder ([Magicoder-S-DS-6.7B-GGUF](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q5_K_S.gguf)) so I started creating a customize Modelfile as follows: ``` FROM ./magicoder-s-ds-6.7b TEMPLATE """{{- if .System }} <|im_start|>system {{ .System }}<|im_end|> {{- end }} <im start|>user {{ .Prompt }}<|im_end|> <|im start|>assistant """ PARAMETER stop "<|im_start|>" PARAMETER stop "<|im_end|>" ``` Then I ran the following command: ``` ollama create pruebaPablo -f ./Modelfile ``` Everyting worked properly with the following output: ``` transferring model data creating model layer creating template layer creating system layer creating parameters layer creating config layer using already created layer sha256:7f0011bbe58c5bd2b3aa81abaa595d0e2181d7fa287a39a5899e7bb9a3117262 writing layer sha256:fbd3a46e44915917bdfe24b8c1cb7bf74f49cf12761b45c9787842b477c5a8fe using already created layer sha256:f02dd72bb2423204352eabc5637b44d79d17f109fdb510a7c51455892aa2d216 writing layer sha256:f37e567548df4ecb18a3ef059c296cc50f0e0a11e5c1eb04b427688b1d4ea3ea writing manifest success ``` But, then, when I execute the run instruction it gets stuck loading and I can not send anything to the model as you can see in the following image: ![image](https://github.com/ollama/ollama/assets/55744688/1a9dd209-fbf3-437c-8689-cfa57e85cc3b) Is there anything I am doing wrong? Many thanks, Pablo.
GiteaMirror added the needs more info label 2026-04-12 11:03:27 -05:00
GiteaMirror commented 2026-04-12 11:03:29 -05:00
Author
Owner
Copy Link

@sola97 commented on GitHub (Mar 3, 2024):

same issue
image

<!-- gh-comment-id:1975020096 --> @sola97 commented on GitHub (Mar 3, 2024): same issue ![image](https://github.com/ollama/ollama/assets/17388849/500d87df-0a69-4bd6-bafc-3ed0f20820f3)
GiteaMirror commented 2026-04-12 11:03:30 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Mar 11, 2024):

Can you attach the ollama server logs when loading this model? Also, what platform (system architecture, operating system, accelerator (GPU) if any) are you using?

<!-- gh-comment-id:1989108341 --> @mxyng commented on GitHub (Mar 11, 2024): Can you attach the ollama server logs when loading this model? Also, what platform (system architecture, operating system, accelerator (GPU) if any) are you using?
GiteaMirror commented 2026-04-12 11:03:30 -05:00
Author
Owner
Copy Link

@sola97 commented on GitHub (Mar 17, 2024):

Can you attach the ollama server logs when loading this model? Also, what platform (system architecture, operating system, accelerator (GPU) if any) are you using?

I suspect it might be due to insufficient GPU memory. After restarting my computer, the model can be fully loaded into VRAM without getting stuck. Issue resolved.

<!-- gh-comment-id:2002456374 --> @sola97 commented on GitHub (Mar 17, 2024): > Can you attach the ollama server logs when loading this model? Also, what platform (system architecture, operating system, accelerator (GPU) if any) are you using? I suspect it might be due to insufficient GPU memory. After restarting my computer, the model can be fully loaded into VRAM without getting stuck. Issue resolved.
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 needs more info
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#1262
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?