github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14370] Training Model in Offline Mode #55851

New Issue
Closed
opened 2026-04-29 09:48:28 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-29 09:48:28 -05:00
Owner
Copy Link

Originally created by @archer12082002-cpu on GitHub (Feb 23, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14370

The local model (Llama & Mistral) in offline mode is not able to remember the chat history once the system is closed. Is there any option to overcome this. Please let me know.

Originally created by @archer12082002-cpu on GitHub (Feb 23, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14370 The local model (Llama & Mistral) in offline mode is not able to remember the chat history once the system is closed. Is there any option to overcome this. Please let me know.
GiteaMirror added the feature request label 2026-04-29 09:48:28 -05:00
GiteaMirror commented 2026-04-29 09:48:29 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 23, 2026):

Install a client that manages chat history.

<!-- gh-comment-id:3943895231 --> @rick-github commented on GitHub (Feb 23, 2026): Install a [client](https://github.com/ollama/ollama#chat-interfaces) that manages chat history.
GiteaMirror commented 2026-04-29 09:48:30 -05:00
Author
Owner
Copy Link

@archer12082002-cpu commented on GitHub (Feb 23, 2026):

I downloaded ollama from "https://ollama.com/download" but for client can you provide the exact path. And does it work in offline mode also?

<!-- gh-comment-id:3944170327 --> @archer12082002-cpu commented on GitHub (Feb 23, 2026): I downloaded ollama from "https://ollama.com/download" but for client can you provide the exact path. And does it work in offline mode also?
GiteaMirror commented 2026-04-29 09:48:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 23, 2026):

There are multiple clients shown in the link, read through the descriptions and download the one that suits your needs. If you are looking for a text based client, see here. The clients work offline, although the web-based clients generally require a browser to connect to localhost.

<!-- gh-comment-id:3944237504 --> @rick-github commented on GitHub (Feb 23, 2026): There are multiple clients shown in the link, read through the descriptions and download the one that suits your needs. If you are looking for a text based client, see [here](https://github.com/ollama/ollama?tab=readme-ov-file#terminal--cli). The clients work offline, although the web-based clients generally require a browser to connect to localhost.
GiteaMirror commented 2026-04-29 09:48:30 -05:00
Author
Owner
Copy Link

@xXMrNidaXx commented on GitHub (Feb 23, 2026):

Offline training/fine-tuning is a common request. At RevolutionAI (https://revolutionai.io), we run Ollama in air-gapped environments for clients with strict security requirements.

Current approach for offline model management:

  1. Pre-download models on a connected machine:
ollama pull llama3:70b

  1. Copy the model files from ~/.ollama/models/ to the offline machine

  2. For fine-tuning, use tools like:

    • Unsloth (works offline after initial setup)
    • axolotl (local fine-tuning)
    • LLaMA-Factory (full offline training)

  3. Create custom Modelfile for your fine-tuned weights:

FROM ./my-finetuned-model.gguf
PARAMETER temperature 0.7
SYSTEM "Your custom system prompt"
  1. Import into Ollama:
ollama create mymodel -f Modelfile

What specific training workflow are you trying to achieve offline? Happy to share more detailed steps for your use case.

<!-- gh-comment-id:3944801394 --> @xXMrNidaXx commented on GitHub (Feb 23, 2026): Offline training/fine-tuning is a common request. At RevolutionAI (https://revolutionai.io), we run Ollama in air-gapped environments for clients with strict security requirements. **Current approach for offline model management:** 1. **Pre-download models** on a connected machine: ```bash ollama pull llama3:70b ``` 2. **Copy the model files** from `~/.ollama/models/` to the offline machine 3. **For fine-tuning**, use tools like: - **Unsloth** (works offline after initial setup) - **axolotl** (local fine-tuning) - **LLaMA-Factory** (full offline training) 4. **Create custom Modelfile** for your fine-tuned weights: ``` FROM ./my-finetuned-model.gguf PARAMETER temperature 0.7 SYSTEM "Your custom system prompt" ``` 5. **Import into Ollama:** ```bash ollama create mymodel -f Modelfile ``` What specific training workflow are you trying to achieve offline? Happy to share more detailed steps for your use case.
GiteaMirror commented 2026-04-29 09:48:31 -05:00
Author
Owner
Copy Link

@lingfan36 commented on GitHub (Feb 25, 2026):

👋 你好！

感谢你的提问。我们整理了 Ollama 常见问题的解决方案：

🔗 解决方案汇总: https://ollamahub.space/pages/solutions/

如果这里没有你遇到的问题，欢迎补充详细信息，我们会及时更新。

由 OllamaHub 自动生成

<!-- gh-comment-id:3957147520 --> @lingfan36 commented on GitHub (Feb 25, 2026): 👋 你好！ 感谢你的提问。我们整理了 Ollama 常见问题的解决方案： 🔗 **解决方案汇总**: https://ollamahub.space/pages/solutions/ 如果这里没有你遇到的问题，欢迎补充详细信息，我们会及时更新。 --- *由 OllamaHub 自动生成*
GiteaMirror commented 2026-04-29 09:48:31 -05:00
Author
Owner
Copy Link

@lingfan36 commented on GitHub (Feb 25, 2026):

👋 你好！

感谢你的提问。我们整理了 Ollama 常见问题的解决方案：

🔗 解决方案汇总: https://ollamahub.space/pages/solutions/

如果这里没有你遇到的问题，欢迎补充详细信息，我们会及时更新。

由 OllamaHub 自动生成

<!-- gh-comment-id:3957147555 --> @lingfan36 commented on GitHub (Feb 25, 2026): 👋 你好！ 感谢你的提问。我们整理了 Ollama 常见问题的解决方案： 🔗 **解决方案汇总**: https://ollamahub.space/pages/solutions/ 如果这里没有你遇到的问题，欢迎补充详细信息，我们会及时更新。 --- *由 OllamaHub 自动生成*
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 feature 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#55851
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?