github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #880] [CLOSED] Temporary Workaround for GGUF v3 Support #57068

New Issue
Closed
opened 2026-04-29 11:39:17 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 11:39:17 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/880
Author: @deichbewohner
Created: 10/23/2023
Status: ❌ Closed

Base: main ← Head: gguf_v3_workaround

📝 Commits (1)

  • 8923fe6 Workaround to support GGUF container specification v3

📊 Changes

1 file changed (+5 additions, -1 deletions)

View changed files

📝 llm/gguf.go (+5 -1)

📄 Description

Addresses the problem raised in Issue #877.

This pull request introduces a temporary workaround to support the GGUF container specification version 3 by treating it as version 2 within the switch case block in llm/gguf.go. This change ensures that the new models utilizing version 3 can be processed correctly in the interim.

I am hesitant to even suggest that such workarounds be merged. However, this branch could serve as a temporary solution for others until a more robust fix is deployed. I intend to use this branch to work with models quantized by TheBloke in the meantime.

I have tested it against new v3 models and v2 models:

$ ollama run agentlm-7b:Q4_K_M "Hi"
Hello! How can I assist you today?

$ ollama run samantha-1.2-mistral-7b:Q4_K_M "Hi"
Hello! I'm glad you decided to say hello. What would you like to talk about today? I'm here for a friendly conversation and to provide support whenever you need it.

$ ollama run zephyr-7b-alpha:Q4_K_M "Hi"
Hello! How can I assist you?

🔄 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/880 **Author:** [@deichbewohner](https://github.com/deichbewohner) **Created:** 10/23/2023 **Status:** ❌ Closed **Base:** `main` ← **Head:** `gguf_v3_workaround` --- ### 📝 Commits (1) - [`8923fe6`](https://github.com/ollama/ollama/commit/8923fe65235780cc67d03de1503b595f998be71e) Workaround to support GGUF container specification v3 ### 📊 Changes **1 file changed** (+5 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `llm/gguf.go` (+5 -1) </details> ### 📄 Description Addresses the problem raised in Issue #877. This pull request introduces a temporary workaround to support the GGUF container specification version 3 by treating it as version 2 within the switch case block in `llm/gguf.go`. This change ensures that the new models utilizing version 3 can be processed correctly in the interim. I am hesitant to even suggest that such workarounds be merged. However, this branch could serve as a temporary solution for others until a more robust fix is deployed. I intend to use this branch to work with models quantized by TheBloke in the meantime. I have tested it against new v3 models and v2 models: ```bash $ ollama run agentlm-7b:Q4_K_M "Hi" Hello! How can I assist you today? $ ollama run samantha-1.2-mistral-7b:Q4_K_M "Hi" Hello! I'm glad you decided to say hello. What would you like to talk about today? I'm here for a friendly conversation and to provide support whenever you need it. $ ollama run zephyr-7b-alpha:Q4_K_M "Hi" Hello! How can I assist you? ``` --- <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 2026-04-29 11:39:17 -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#57068
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?