github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 13:47:08 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #15765] docs: add HuggingFace Hub direct GGUF pull pattern to import guide #77593

New Issue
Open
opened 2026-05-05 10:15:43 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 10:15:43 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15765
Author: @rudi193-cmd
Created: 4/23/2026
Status: 🔄 Open

Base: main ← Head: docs/hf-hub-gguf-pull

📝 Commits (1)

  • ceedbc9 docs: add HuggingFace Hub direct GGUF pull pattern to import guide

📊 Changes

1 file changed (+50 additions, -0 deletions)

View changed files

📝 docs/import.mdx (+50 -0)

📄 Description

Summary

The import guide covers converting GGUF files locally but doesn't document the ollama pull hf.co/owner/repo:tag pattern for pulling GGUF files directly from Hugging Face Hub.

This is increasingly the most common workflow for fine-tuned models: train → export GGUF → upload to HF Hub → ollama pull hf.co/....

Adds a new section covering:

  • Direct pull via hf.co/ prefix
  • Creating a local alias with ollama cp (useful for multi-version workflows)
  • Customising system prompt and parameters via a minimal Modelfile on top of a hub-pulled model

Tested with hf.co/Rudi193/yggdrasil-v9:Q4_K_M across v1–v9 training iterations of a domain-specific fine-tuned model.

🔄 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/15765 **Author:** [@rudi193-cmd](https://github.com/rudi193-cmd) **Created:** 4/23/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `docs/hf-hub-gguf-pull` --- ### 📝 Commits (1) - [`ceedbc9`](https://github.com/ollama/ollama/commit/ceedbc9c393a7f7e382cbfd500912336b6a30871) docs: add HuggingFace Hub direct GGUF pull pattern to import guide ### 📊 Changes **1 file changed** (+50 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `docs/import.mdx` (+50 -0) </details> ### 📄 Description ## Summary The import guide covers converting GGUF files locally but doesn't document the `ollama pull hf.co/owner/repo:tag` pattern for pulling GGUF files directly from Hugging Face Hub. This is increasingly the most common workflow for fine-tuned models: train → export GGUF → upload to HF Hub → `ollama pull hf.co/...`. Adds a new section covering: - Direct pull via `hf.co/` prefix - Creating a local alias with `ollama cp` (useful for multi-version workflows) - Customising system prompt and parameters via a minimal Modelfile on top of a hub-pulled model Tested with `hf.co/Rudi193/yggdrasil-v9:Q4_K_M` across v1–v9 training iterations of a domain-specific fine-tuned model. --- <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 10:15:43 -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#77593
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?