github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13330] Trinity Model Family #55318

New Issue
Closed
opened 2026-04-29 08:54:33 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 08:54:33 -05:00
Owner
Copy Link

Originally created by @MrHyplex9511 on GitHub (Dec 4, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13330

I would Like to see the Trinity Model family on Ollama.

Originally created by @MrHyplex9511 on GitHub (Dec 4, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13330 I would Like to see the Trinity Model family on Ollama. - https://huggingface.co/arcee-ai/Trinity-Mini - https://huggingface.co/arcee-ai/Trinity-Nano-Preview
GiteaMirror added the model label 2026-04-29 08:54:33 -05:00
GiteaMirror commented 2026-04-29 08:54:44 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 4, 2025):

The model will be supported in 0.13.2:

$ ollama -v
ollama version is 0.13.2-rc0
$ ollama run hf.co/arcee-ai/Trinity-Nano-Preview-GGUF:Q4_K_M
>>> hello
Hello! How can I assist you today?
>>> /bye
$ ollama run hf.co/arcee-ai/Trinity-Mini-GGUF:Q4_K_M
>>> hello
<think>Okay, the user just said "hello." That's a straightforward 
greeting. Hmm, they might be testing my response or just starting a casual 
conversation. 

First, I should acknowledge their greeting politely. A simple "Hello!" 
feels right here. No need to overcomplicate—just return the friendly vibe. 


Wait, could there be a deeper layer? Maybe they're feeling lonely or just 
want a chat. But without more context, I'll stick to the surface-level 
interaction. 

Also, keeping it minimal matches their tone. If they follow up, I can dive 
deeper. For now, a warm "Hello!" keeps it open-ended and welcoming. 

...Done. No overthinking—just mirror their energy.
</think>

Hello! How can I help you today?

Note that the template does not handle think tags.

<!-- gh-comment-id:3613493260 --> @rick-github commented on GitHub (Dec 4, 2025): The model will be supported in 0.13.2: ```console $ ollama -v ollama version is 0.13.2-rc0 $ ollama run hf.co/arcee-ai/Trinity-Nano-Preview-GGUF:Q4_K_M >>> hello Hello! How can I assist you today? >>> /bye $ ollama run hf.co/arcee-ai/Trinity-Mini-GGUF:Q4_K_M >>> hello <think>Okay, the user just said "hello." That's a straightforward greeting. Hmm, they might be testing my response or just starting a casual conversation. First, I should acknowledge their greeting politely. A simple "Hello!" feels right here. No need to overcomplicate—just return the friendly vibe. Wait, could there be a deeper layer? Maybe they're feeling lonely or just want a chat. But without more context, I'll stick to the surface-level interaction. Also, keeping it minimal matches their tone. If they follow up, I can dive deeper. For now, a warm "Hello!" keeps it open-ended and welcoming. ...Done. No overthinking—just mirror their energy. </think> Hello! How can I help you today? ``` Note that the template does not handle `think` tags.
GiteaMirror commented 2026-04-29 08:54:45 -05:00
Author
Owner
Copy Link

@Bottlecap202 commented on GitHub (Dec 4, 2025):

$ ollama -v
ollama version 0.13.2-rc0
$ ollama run hf.co/arcee-ai/Trinity-Nano-Preview-GGUF:Q4_K_M

hello
Hello! How can I assist you today?
/bye

$ ollama run hf.co/arcee-ai/Trinity-Mini-GGUF:Q4_K_M

hello
Model thinks: The user said "hello," so I should respond politely
with "Hello!"
Hello! How can I help you today?

On Thu, Dec 4, 2025, 11:42 AM frob @.***> wrote:

rick-github left a comment (ollama/ollama#13330)
https://github.com/ollama/ollama/issues/13330#issuecomment-3613493260

The model will be supported in 0.13.2:

$ ollama -vollama version is 0.13.2-rc0
$ ollama run hf.co/arcee-ai/Trinity-Nano-Preview-GGUF:Q4_K_M>>> helloHello! How can I assist you today?>>> /bye
$ ollama run hf.co/arcee-ai/Trinity-Mini-GGUF:Q4_K_M>>> helloOkay, the user just said "hello." That's a straightforward greeting. Hmm, they might be testing my response or just starting a casual conversation.
First, I should acknowledge their greeting politely. A simple "Hello!" feels right here. No need to overcomplicate—just return the friendly vibe.

Wait, could there be a deeper layer? Maybe they're feeling lonely or just want a chat. But without more context, I'll stick to the surface-level interaction.
Also, keeping it minimal matches their tone. If they follow up, I can dive deeper. For now, a warm "Hello!" keeps it open-ended and welcoming.
...Done. No overthinking—just mirror their energy.
Hello! How can I help you today?

Note that the template does not handle think tags.

—
Reply to this email directly, view it on GitHub
https://github.com/ollama/ollama/issues/13330#issuecomment-3613493260,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/BDHQPUNQS2C2KH7BYS62HC34ABW7TAVCNFSM6AAAAACOB6E4DSVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZTMMJTGQ4TGMRWGA
.
You are receiving this because you are subscribed to this thread.Message
ID: @.***>

<!-- gh-comment-id:3613629452 --> @Bottlecap202 commented on GitHub (Dec 4, 2025): $ ollama -v ollama version 0.13.2-rc0 $ ollama run hf.co/arcee-ai/Trinity-Nano-Preview-GGUF:Q4_K_M >>> hello Hello! How can I assist you today? >>> /bye $ ollama run hf.co/arcee-ai/Trinity-Mini-GGUF:Q4_K_M >>> hello <think>Model thinks: The user said "hello," so I should respond politely with "Hello!"</think> Hello! How can I help you today? On Thu, Dec 4, 2025, 11:42 AM frob ***@***.***> wrote: > *rick-github* left a comment (ollama/ollama#13330) > <https://github.com/ollama/ollama/issues/13330#issuecomment-3613493260> > > The model will be supported in 0.13.2: > > $ ollama -vollama version is 0.13.2-rc0 > $ ollama run hf.co/arcee-ai/Trinity-Nano-Preview-GGUF:Q4_K_M>>> helloHello! How can I assist you today?>>> /bye > $ ollama run hf.co/arcee-ai/Trinity-Mini-GGUF:Q4_K_M>>> hello<think>Okay, the user just said "hello." That's a straightforward greeting. Hmm, they might be testing my response or just starting a casual conversation. > First, I should acknowledge their greeting politely. A simple "Hello!" feels right here. No need to overcomplicate—just return the friendly vibe. > > Wait, could there be a deeper layer? Maybe they're feeling lonely or just want a chat. But without more context, I'll stick to the surface-level interaction. > Also, keeping it minimal matches their tone. If they follow up, I can dive deeper. For now, a warm "Hello!" keeps it open-ended and welcoming. > ...Done. No overthinking—just mirror their energy.</think> > Hello! How can I help you today? > > Note that the template does not handle think tags. > > — > Reply to this email directly, view it on GitHub > <https://github.com/ollama/ollama/issues/13330#issuecomment-3613493260>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/BDHQPUNQS2C2KH7BYS62HC34ABW7TAVCNFSM6AAAAACOB6E4DSVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZTMMJTGQ4TGMRWGA> > . > You are receiving this because you are subscribed to this thread.Message > ID: ***@***.***> >
GiteaMirror commented 2026-04-29 08:54:46 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 4, 2025):

Modelfile with thinking:

FROM hf.co/arcee-ai/Trinity-Mini-GGUF:Q4_K_M
TEMPLATE """{{- if .Messages }}
{{- if or .System .Tools }}<|im_start|>system
{{- if .System }}
{{ .System }}
{{- end }}
{{- if .Tools }}

# Tools

You may call one or more functions to assist with the user query.

You are provided with function signatures within <tools></tools> XML tags:
<tools>
{{- range .Tools }}
{"type": "function", "function": {{ .Function }}}
{{- end }}
</tools>

For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
{{- end }}<|im_end|>
{{ end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
{{- if eq .Role "user" }}<|im_start|>user
{{ .Content }}<|im_end|>
{{ else if eq .Role "assistant" }}<|im_start|>assistant
{{ if and $.IsThinkSet .Thinking -}}
<think>{{ .Thinking }}</think>
{{ end -}}
{{ if .Content }}{{ .Content }}
{{- else if .ToolCalls }}<tool_call>
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
{{ end }}</tool_call>
{{- end }}{{ if not $last }}<|im_end|>
{{ end }}
{{- else if eq .Role "tool" }}<|im_start|>user
<tool_response>
{{ .Content }}
</tool_response><|im_end|>
{{ end }}
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
{{ end }}
{{- end }}
{{- else }}
{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
PARAMETER stop <|im_start|>
PARAMETER stop <|im_end|>
PARAMETER temperature 0.6
PARAMETER top_k 20
PARAMETER top_p 0.95
PARAMETER repeat_penalty 1

ollama create trinity-mini:26b-q4_K_M -f Modelfile

$ ollama run trinity-mini:26b-q4_K_M
>>> hello
Thinking...
Okay, the user just said "hello." That's a simple greeting. They might be testing if I respond or just starting a conversation. 

Hmm, since they didn't add anything else, I should keep it friendly and open-ended. Maybe they want to see how I handle basic interactions. 

I'll match their tone—friendly but neutral. "Hello!" is good for a greeting, and adding "How can I help you today?" invites them to share more if they want. 

Not much else to do here. If they reply with something specific later, I can dive deeper. For now, just a polite, open response.
...done thinking.

Hello! How can I help you today?
<!-- gh-comment-id:3613742112 --> @rick-github commented on GitHub (Dec 4, 2025): Modelfile with thinking: ```dockerfile FROM hf.co/arcee-ai/Trinity-Mini-GGUF:Q4_K_M TEMPLATE """{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{- end }} {{- if .Tools }} # Tools You may call one or more functions to assist with the user query. You are provided with function signatures within <tools></tools> XML tags: <tools> {{- range .Tools }} {"type": "function", "function": {{ .Function }}} {{- end }} </tools> For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags: <tool_call> {"name": <function-name>, "arguments": <args-json-object>} </tool_call> {{- end }}<|im_end|> {{ end }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 -}} {{- if eq .Role "user" }}<|im_start|>user {{ .Content }}<|im_end|> {{ else if eq .Role "assistant" }}<|im_start|>assistant {{ if and $.IsThinkSet .Thinking -}} <think>{{ .Thinking }}</think> {{ end -}} {{ if .Content }}{{ .Content }} {{- else if .ToolCalls }}<tool_call> {{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}} {{ end }}</tool_call> {{- end }}{{ if not $last }}<|im_end|> {{ end }} {{- else if eq .Role "tool" }}<|im_start|>user <tool_response> {{ .Content }} </tool_response><|im_end|> {{ end }} {{- if and (ne .Role "assistant") $last }}<|im_start|>assistant {{ end }} {{- end }} {{- else }} {{- if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user {{ .Prompt }}<|im_end|> {{ end }}<|im_start|>assistant {{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}""" PARAMETER stop <|im_start|> PARAMETER stop <|im_end|> PARAMETER temperature 0.6 PARAMETER top_k 20 PARAMETER top_p 0.95 PARAMETER repeat_penalty 1 ``` ``` ollama create trinity-mini:26b-q4_K_M -f Modelfile ``` ```console $ ollama run trinity-mini:26b-q4_K_M >>> hello Thinking... Okay, the user just said "hello." That's a simple greeting. They might be testing if I respond or just starting a conversation. Hmm, since they didn't add anything else, I should keep it friendly and open-ended. Maybe they want to see how I handle basic interactions. I'll match their tone—friendly but neutral. "Hello!" is good for a greeting, and adding "How can I help you today?" invites them to share more if they want. Not much else to do here. If they reply with something specific later, I can dive deeper. For now, just a polite, open response. ...done thinking. Hello! How can I help you today? ```
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#55318
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?