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 #6671] Reflection 70B NEED Tools #66235

New Issue
Closed
opened 2026-05-04 01:08:18 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-04 01:08:18 -05:00
Owner
Copy Link

Originally created by @tianyang2026 on GitHub (Sep 6, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6671

Reflection 70B NEED Tools

Originally created by @tianyang2026 on GitHub (Sep 6, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6671 Reflection 70B NEED Tools
GiteaMirror added the model label 2026-05-04 01:08:18 -05:00
GiteaMirror commented 2026-05-04 01:08:33 -05:00
Author
Owner
Copy Link

@Utopiah commented on GitHub (Sep 6, 2024):

Is this covered by https://github.com/ollama/ollama/issues/6664 ?

<!-- gh-comment-id:2334123241 --> @Utopiah commented on GitHub (Sep 6, 2024): Is this covered by https://github.com/ollama/ollama/issues/6664 ?
GiteaMirror commented 2026-05-04 01:08:43 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 6, 2024):

Since Reflection is based on llama3.1, you might be able to take the template from llama3.1 and use that in place of the current one.

<!-- gh-comment-id:2334173644 --> @rick-github commented on GitHub (Sep 6, 2024): Since Reflection is based on llama3.1, you might be able to take the [template](https://ollama.com/library/llama3.1/blobs/73b313b5552d) from llama3.1 and use that in place of the current one.
GiteaMirror commented 2026-05-04 01:08:50 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 6, 2024):

I tried using the llama3.1 template and needs some work. Because of the <thinking>, <reflection> and <output> stages, the model ends up making three tool calls for every query.

<!-- gh-comment-id:2334711557 --> @rick-github commented on GitHub (Sep 6, 2024): I tried using the llama3.1 template and needs some work. Because of the \<thinking\>, \<reflection\> and \<output\> stages, the model ends up making three tool calls for every query.
GiteaMirror commented 2026-05-04 01:08:57 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Sep 6, 2024):

@rick-github that was my worry. I don't think this model is designed for tool calling. If it is, we can re-open this issue. Thanks for giving it a try, I was curious :)

<!-- gh-comment-id:2334825843 --> @jmorganca commented on GitHub (Sep 6, 2024): @rick-github that was my worry. I don't think this model is designed for tool calling. If it is, we can re-open this issue. Thanks for giving it a try, I was curious :)
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 model
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#66235
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?