github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #15953] LiquidAI/lfm2.5-1.2b-instruct and LiquidAI/lfm2.5-350m don't accept tool calling even though they support it #87847

New Issue
Closed
opened 2026-05-10 06:26:53 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-10 06:26:53 -05:00
Owner
Copy Link

Originally created by @ajitsingh-tf on GitHub (May 4, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15953

What is the issue?

If you read their descriptions

you'd see both models support tool calling

but when I run

ollama launch pi --model LiquidAI/lfm2.5-1.2b-instruct

and I put any prompt and hit enter, I get:

Error: 400 registry.ollama.ai/liquidai/lfm2.5-1.2b-instruct:latest does not support tools

Expected Behavior: I suppose we need to add "tools" tag in those so that it doesn't give 400.

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.22.0

Originally created by @ajitsingh-tf on GitHub (May 4, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15953 ### What is the issue? If you read their descriptions - https://ollama.com/LiquidAI/lfm2.5-350m - https://ollama.com/LiquidAI/lfm2.5-1.2b-instruct you'd see both models support tool calling but when I run ``` ollama launch pi --model LiquidAI/lfm2.5-1.2b-instruct ``` and I put any prompt and hit enter, I get: ``` Error: 400 registry.ollama.ai/liquidai/lfm2.5-1.2b-instruct:latest does not support tools ``` **Expected Behavior**: I suppose we need to add "tools" tag in those so that it doesn't give 400. ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.22.0
GiteaMirror added the bug label 2026-05-10 06:26:53 -05:00
GiteaMirror commented 2026-05-10 06:26:57 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 4, 2026):

These are user uploaded models and the supplied Modelfile doesn't provide tool support.

Fortunately the chat template for these models is the same as for lfm2, which ollama supports. So the Modelfile can be modified to use the RENDERER and PARSER from the official lfm2 models.

$ ollama show --modelfile liquidai/lfm2.5-1.2b-instruct:q8_0 | grep -v '{{' > Modelfile
$ echo RENDERER lfm2 >> Modelfile
$ echo PARSER lfm2 >> Modelfile
$ ollama create lfm2.5-1.2b-instruct:q8_0

$ ollama run lfm2.5-1.2b-instruct:q8_0 --experimental --experimental-yolo

This experimental version of Ollama has the bash tool enabled.
Models can read files on your computer, or run commands (after you allow them).

warning: yolo mode - all tool approvals will be skipped
>>> what is the time?

running: Bash: date
  Mon May  4 09:32:13 AM CEST 2026
  

The current time is May 4, 2026 at 09:32 AM CEST.

Be aware that small models are generally not great tool users.

<!-- gh-comment-id:4369113631 --> @rick-github commented on GitHub (May 4, 2026): These are user uploaded models and the supplied Modelfile doesn't provide tool support. Fortunately the [chat template](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking/blob/main/chat_template.jinja) for these models is the same as for lfm2, which ollama supports. So the Modelfile can be modified to use the RENDERER and PARSER from the official lfm2 models. ```console $ ollama show --modelfile liquidai/lfm2.5-1.2b-instruct:q8_0 | grep -v '{{' > Modelfile $ echo RENDERER lfm2 >> Modelfile $ echo PARSER lfm2 >> Modelfile $ ollama create lfm2.5-1.2b-instruct:q8_0 ``` ```console $ ollama run lfm2.5-1.2b-instruct:q8_0 --experimental --experimental-yolo This experimental version of Ollama has the bash tool enabled. Models can read files on your computer, or run commands (after you allow them). warning: yolo mode - all tool approvals will be skipped >>> what is the time? running: Bash: date Mon May 4 09:32:13 AM CEST 2026 The current time is May 4, 2026 at 09:32 AM CEST. ``` Be aware that small models are generally not great tool users.
GiteaMirror commented 2026-05-10 06:26:57 -05:00
Author
Owner
Copy Link

@ajitsingh-tf commented on GitHub (May 4, 2026):

Thanks Rick! Closing.

<!-- gh-comment-id:4369134917 --> @ajitsingh-tf commented on GitHub (May 4, 2026): Thanks Rick! Closing.
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#87847
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?