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

[PR #6514] [MERGED] Implicit openai model parameter multiplication disabled #74427

New Issue
Closed
opened 2026-05-05 06:30:17 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 06:30:17 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/6514
Author: @yaroslavyaroslav
Created: 8/26/2024
Status: ✅ Merged
Merged: 9/7/2024
Merged by: @jmorganca

Base: main ← Head: patch-1

📝 Commits (2)

  • d2461f0 Implicit openai model parameter multiplication disabled
  • a0daca0 Update openai_test.go

📊 Changes

2 files changed (+4 additions, -4 deletions)

View changed files

📝 openai/openai.go (+3 -3)
📝 openai/openai_test.go (+1 -1)

📄 Description

Current state of openai.go setup makes absolutely valid openai config to be broken. This happens because of implicit doubling the config numbers performed in it.

I see the idea of making OpenAI API endpoint compatible with native ollama endpoint, but I think it've made wrong, as again, it leads to completely valid OpenAI config makes model goes wild.

Thus user is unable to use the same config for openai and ollama without modifications outside of model's field.

{
    "url": "http://localhost:11434",
    "token": "sk-your-token",
    "status_hint": [
        "name",
        "prompt_mode",
        "chat_model"
    ],
    "assistants": [
        {
            "name": "qwen2",
            "chat_model": "qwen2:1.5b",
            "assistant_role": "You are a senior python and sublime text 4 code assistant",
            "prompt_mode": "panel",
            "temperature": 1, // makes model go insane, coz the temperature is 2 on ollama's side.
            "max_tokens": 1048,
            "top_p": 1,
            "frequency_penalty": 0, // doubles as well
            "presence_penalty": 0, // doubles as well
        }
    ]
}

Closes: #6492
Affects: https://github.com/yaroslavyaroslav/OpenAI-sublime-text/issues/57

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/6514 **Author:** [@yaroslavyaroslav](https://github.com/yaroslavyaroslav) **Created:** 8/26/2024 **Status:** ✅ Merged **Merged:** 9/7/2024 **Merged by:** [@jmorganca](https://github.com/jmorganca) **Base:** `main` ← **Head:** `patch-1` --- ### 📝 Commits (2) - [`d2461f0`](https://github.com/ollama/ollama/commit/d2461f0b49a379cc134c7445d4e242ff441fc29b) Implicit openai model parameter multiplication disabled - [`a0daca0`](https://github.com/ollama/ollama/commit/a0daca0f985e26cb62d843188da6d26dfeab4aa6) Update openai_test.go ### 📊 Changes **2 files changed** (+4 additions, -4 deletions) <details> <summary>View changed files</summary> 📝 `openai/openai.go` (+3 -3) 📝 `openai/openai_test.go` (+1 -1) </details> ### 📄 Description Current state of openai.go setup makes absolutely valid openai config to be broken. This happens because of implicit doubling the config numbers performed in it. I see the idea of making OpenAI API endpoint compatible with native ollama endpoint, but I think it've made wrong, as again, it leads to completely valid OpenAI config makes model goes wild. Thus user is unable to use the same config for openai and ollama without modifications outside of model's field. ```json { "url": "http://localhost:11434", "token": "sk-your-token", "status_hint": [ "name", "prompt_mode", "chat_model" ], "assistants": [ { "name": "qwen2", "chat_model": "qwen2:1.5b", "assistant_role": "You are a senior python and sublime text 4 code assistant", "prompt_mode": "panel", "temperature": 1, // makes model go insane, coz the temperature is 2 on ollama's side. "max_tokens": 1048, "top_p": 1, "frequency_penalty": 0, // doubles as well "presence_penalty": 0, // doubles as well } ] } ``` Closes: #6492 Affects: https://github.com/yaroslavyaroslav/OpenAI-sublime-text/issues/57 --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-05-05 06:30:17 -05:00
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 pull-request
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#74427
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?