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 #3977] api/create inserts escape quotes \" for the last PARAMETER stop. #64498

New Issue
Closed
opened 2026-05-03 17:54:03 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 17:54:03 -05:00
Owner
Copy Link

Originally created by @chigkim on GitHub (Apr 27, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3977

What is the issue?

Hi,

If you run the following python code to copy llama3 to test, it creates a modelfile with escape qotes for the last PARAMETER stop.
If I use ollama create test -f test.modelfile, it works fine.
First I thought ollama/ollama-python was the problem, but I tried with just python requests library, and it had the same problem.

from ollama import Client
import re

client = Client(host='http://localhost:11434')
modelfile = client.show('llama3')['modelfile']
print('Original modelfile:\n', modelfile)
from_str = re.search('# (FROM.*?\n)', modelfile)[1]
modelfile = re.sub('FROM /Users.*?\n', from_str, modelfile)
print('Modified modelfile:\n', modelfile)
client.create('test', modelfile=modelfile, stream=False)
response = client.generate(model='test', prompt='hello!')
print('Response:\n', response['response'])
modelfile = client.show('test')['modelfile']
print('new modelfile:\n', modelfile)
client.delete('test')

Here's the output.

Original modelfile:
 # Modelfile generated by "ollama show"
# To build a new Modelfile based on this one, replace the FROM line with:
# FROM llama3:latest

FROM /Users/cgk/.ollama/models/blobs/sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ .Response }}<|eot_id|>"""
PARAMETER num_keep 24
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
Modified modelfile:
 # Modelfile generated by "ollama show"
# To build a new Modelfile based on this one, replace the FROM line with:
# FROM llama3:latest

FROM llama3:latest
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ .Response }}<|eot_id|>"""
PARAMETER num_keep 24
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
Response:
 Hello there! It's nice to meet you. Is there something I can help you with, or would you like to chat?<|eot_id|>
new modelfile:
 # Modelfile generated by "ollama show"
# To build a new Modelfile based on this one, replace the FROM line with:
# FROM test:latest

FROM llama3:latest
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ .Response }}<|eot_id|>"""
PARAMETER num_keep 24
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "\"<|eot_id|>\""

If you look at the last line, there's the escape quotes ". Not sure why only the last line has that.
Also if you look at the response string, it ends with <|eot_id|> because the last PARAMETER stop string in the new modelfile doesn't work.

The following python code that uses requests library has the same problem.

import requests
url ='http://localhost:11434/api/create'
data = {'name': 'test', 'modelfile': modelfile, 'stream': False}
response = requests.post(url, json=data)

Could you look into this?
Thanks so much!

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.32

Originally created by @chigkim on GitHub (Apr 27, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3977 ### What is the issue? Hi, If you run the following python code to copy llama3 to test, it creates a modelfile with escape qotes for the last PARAMETER stop. If I use `ollama create test -f test.modelfile`, it works fine. First I thought [ollama/ollama-python](https://github.com/ollama/ollama-python/issues/136) was the problem, but I tried with just python requests library, and it had the same problem. ```python from ollama import Client import re client = Client(host='http://localhost:11434') modelfile = client.show('llama3')['modelfile'] print('Original modelfile:\n', modelfile) from_str = re.search('# (FROM.*?\n)', modelfile)[1] modelfile = re.sub('FROM /Users.*?\n', from_str, modelfile) print('Modified modelfile:\n', modelfile) client.create('test', modelfile=modelfile, stream=False) response = client.generate(model='test', prompt='hello!') print('Response:\n', response['response']) modelfile = client.show('test')['modelfile'] print('new modelfile:\n', modelfile) client.delete('test') ``` Here's the output. ```bash Original modelfile: # Modelfile generated by "ollama show" # To build a new Modelfile based on this one, replace the FROM line with: # FROM llama3:latest FROM /Users/cgk/.ollama/models/blobs/sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29 TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>""" PARAMETER num_keep 24 PARAMETER stop "<|start_header_id|>" PARAMETER stop "<|end_header_id|>" PARAMETER stop "<|eot_id|>" Modified modelfile: # Modelfile generated by "ollama show" # To build a new Modelfile based on this one, replace the FROM line with: # FROM llama3:latest FROM llama3:latest TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>""" PARAMETER num_keep 24 PARAMETER stop "<|start_header_id|>" PARAMETER stop "<|end_header_id|>" PARAMETER stop "<|eot_id|>" Response: Hello there! It's nice to meet you. Is there something I can help you with, or would you like to chat?<|eot_id|> new modelfile: # Modelfile generated by "ollama show" # To build a new Modelfile based on this one, replace the FROM line with: # FROM test:latest FROM llama3:latest TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>""" PARAMETER num_keep 24 PARAMETER stop "<|start_header_id|>" PARAMETER stop "<|end_header_id|>" PARAMETER stop "\"<|eot_id|>\"" ``` If you look at the last line, there's the escape quotes \". Not sure why only the last line has that. Also if you look at the response string, it ends with <|eot_id|> because the last PARAMETER stop string in the new modelfile doesn't work. The following python code that uses requests library has the same problem. ```python import requests url ='http://localhost:11434/api/create' data = {'name': 'test', 'modelfile': modelfile, 'stream': False} response = requests.post(url, json=data) ``` Could you look into this? Thanks so much! ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-05-03 17:54:03 -05:00
GiteaMirror commented 2026-05-03 17:54:07 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (May 2, 2024):

this is a bug with the parser and will be fixed by #3892

<!-- gh-comment-id:2091824076 --> @mxyng commented on GitHub (May 2, 2024): this is a bug with the parser and will be fixed by #3892
GiteaMirror commented 2026-05-03 17:54:07 -05:00
Author
Owner
Copy Link

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

Awesome,! Thanks!

<!-- gh-comment-id:2093178320 --> @chigkim commented on GitHub (May 3, 2024): Awesome,! Thanks!
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#64498
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?