[GH-ISSUE #3992] how to config octopus on ollama ? #2470

Closed
opened 2026-04-12 12:48:07 -05:00 by GiteaMirror · 4 comments
Owner

Originally created by @taozhiyuai on GitHub (Apr 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3992

What is the issue?

this is output of octopus on my MAC. anyone know how to config it for better output?

Set 'verbose' mode.

hi
<nexa_end>

Response: <nexa_13>('hi')<nexa_end>

Function description:
def search_youtube_videos(query):
"""
Searches YouTube for videos matching a query.

Parameters:
- query (str): Search query.

Returns:
- list[str]: A list of strings, each string includes video names and 

URLs.
"""

total duration: 1.008565s
load duration: 2.621042ms
prompt eval count: 9 token(s)
prompt eval duration: 109.909ms
prompt eval rate: 81.89 tokens/s
eval count: 82 token(s)
eval duration: 890.205ms
eval rate: 92.11 tokens/s

/show modelfile

Modelfile generated by "ollama show"

To build a new Modelfile based on this one, replace the FROM line with:

FROM octopus-v2-q8:latest

FROM /Users/taozhiyu/.ollama/models/blobs/sha256-a85db45807a0d26b2c14753cea10f947a26196bde3770c95a2d0688b1bd6c127
TEMPLATE """{{ .System }}
USER: {{ .Prompt }}
ASSISTANT: """
PARAMETER num_ctx 4096
PARAMETER stop ""
PARAMETER stop "USER:"
PARAMETER stop ""ASSISTANT:""

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.32

Originally created by @taozhiyuai on GitHub (Apr 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3992 ### What is the issue? this is output of octopus on my MAC. anyone know how to config it for better output? Set 'verbose' mode. >>> hi <nexa_end> Response: <nexa_13>('hi')<nexa_end> Function description: def search_youtube_videos(query): """ Searches YouTube for videos matching a query. Parameters: - query (str): Search query. Returns: - list[str]: A list of strings, each string includes video names and URLs. """ total duration: 1.008565s load duration: 2.621042ms prompt eval count: 9 token(s) prompt eval duration: 109.909ms prompt eval rate: 81.89 tokens/s eval count: 82 token(s) eval duration: 890.205ms eval rate: 92.11 tokens/s >>> /show modelfile # Modelfile generated by "ollama show" # To build a new Modelfile based on this one, replace the FROM line with: # FROM octopus-v2-q8:latest FROM /Users/taozhiyu/.ollama/models/blobs/sha256-a85db45807a0d26b2c14753cea10f947a26196bde3770c95a2d0688b1bd6c127 TEMPLATE """{{ .System }} USER: {{ .Prompt }} ASSISTANT: """ PARAMETER num_ctx 4096 PARAMETER stop "</s>" PARAMETER stop "USER:" PARAMETER stop "\"ASSISTANT:\"" ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-04-12 12:48:07 -05:00
Author
Owner

@taozhiyuai commented on GitHub (Apr 28, 2024):

I import gguf from https://hf-mirror.com/second-state/Octopus-v2-GGUF

<!-- gh-comment-id:2081324483 --> @taozhiyuai commented on GitHub (Apr 28, 2024): I import gguf from https://hf-mirror.com/second-state/Octopus-v2-GGUF
Author
Owner

@Single430 commented on GitHub (May 21, 2024):

Hello, have you solved the problem now? When I registered octopus in Ollama, the Modelfile file kept being written incorrectly, resulting in inncorrect output. Can you help me with this @taozhiyuai

<!-- gh-comment-id:2122194122 --> @Single430 commented on GitHub (May 21, 2024): Hello, have you solved the problem now? When I registered octopus in Ollama, the Modelfile file kept being written incorrectly, resulting in inncorrect output. Can you help me with this @taozhiyuai
Author
Owner

@taozhiyuai commented on GitHub (May 26, 2024):

https://ollama.com/taozhiyuai/octopus-v4 @Single430

<!-- gh-comment-id:2131951103 --> @taozhiyuai commented on GitHub (May 26, 2024): https://ollama.com/taozhiyuai/octopus-v4 @Single430
Author
Owner

@Single430 commented on GitHub (May 26, 2024):

https://ollama.com/taozhiyuai/octopus-v4 @Single430

Thank you, I saw this.

<!-- gh-comment-id:2132229636 --> @Single430 commented on GitHub (May 26, 2024): > https://ollama.com/taozhiyuai/octopus-v4 @Single430 Thank you, I saw this.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2470