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

[GH-ISSUE #4341] how to import Meta-Llama-3-120B-Instruct.imatrix #2704

New Issue
Closed
opened 2026-04-12 13:01:26 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 13:01:26 -05:00
Owner
Copy Link

Originally created by @taozhiyuai on GitHub (May 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4341

WX20240511-115426@2x

I want to import this model. may I know how to import Meta-Llama-3-120B-Instruct.imatrix?

Originally created by @taozhiyuai on GitHub (May 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4341 ![WX20240511-115426@2x](https://github.com/ollama/ollama/assets/146583103/93328322-5cb6-48f8-a538-a99d03ce047e) I want to import this model. may I know how to import Meta-Llama-3-120B-Instruct.imatrix?
GiteaMirror added the feature request label 2026-04-12 13:01:26 -05:00
GiteaMirror commented 2026-04-12 13:01:27 -05:00
Author
Owner
Copy Link

@taozhiyuai commented on GitHub (May 11, 2024):

is it the right model file? or I should merge them into one GGUF?

FROM ./Meta-Llama-3-120B-Instruct-Q5_K_M-00001-of-00003.gguf
FROM ./Meta-Llama-3-120B-Instruct-Q5_K_M-00002-of-00003.gguf
FROM ./Meta-Llama-3-120B-Instruct-Q5_K_M-00003-of-00003.gguf
FROM ./Meta-Llama-3-120B-Instruct.imatrix

TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ .Response }}<|eot_id|>"""
PARAMETER num_keep 24
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"

<!-- gh-comment-id:2105538710 --> @taozhiyuai commented on GitHub (May 11, 2024): is it the right model file? or I should merge them into one GGUF? FROM ./Meta-Llama-3-120B-Instruct-Q5_K_M-00001-of-00003.gguf FROM ./Meta-Llama-3-120B-Instruct-Q5_K_M-00002-of-00003.gguf FROM ./Meta-Llama-3-120B-Instruct-Q5_K_M-00003-of-00003.gguf FROM ./Meta-Llama-3-120B-Instruct.imatrix TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>""" PARAMETER num_keep 24 PARAMETER stop "<|start_header_id|>" PARAMETER stop "<|end_header_id|>" PARAMETER stop "<|eot_id|>"
GiteaMirror commented 2026-04-12 13:01:28 -05:00
Author
Owner
Copy Link

@DuckyBlender commented on GitHub (May 23, 2024):

You can merge them into one GGUF using llama.cpp, they have more info in the quantisation section in the README

<!-- gh-comment-id:2126781372 --> @DuckyBlender commented on GitHub (May 23, 2024): You can merge them into one GGUF using llama.cpp, they have more info in the quantisation section in the README
GiteaMirror commented 2026-04-12 13:01:28 -05:00
Author
Owner
Copy Link

@Milor123 commented on GitHub (Aug 28, 2024):

@DuckyBlender Need use it for use iMatrix? or just should ignore iMatrix and use q6 gguf version? I want import a model and it have a iMatrix but i dont know if should ignore it.
image
Is it bad?

<!-- gh-comment-id:2313866915 --> @Milor123 commented on GitHub (Aug 28, 2024): @DuckyBlender Need use it for use iMatrix? or just should ignore iMatrix and use q6 gguf version? I want import a model and it have a iMatrix but i dont know if should ignore it. ![image](https://github.com/user-attachments/assets/6bb669b7-a082-4e6f-9da2-ccae45c79e29) Is it bad?
GiteaMirror commented 2026-04-12 13:01:28 -05:00
Author
Owner
Copy Link

@DuckyBlender commented on GitHub (Aug 28, 2024):

Sorry, not familiar with I quants

<!-- gh-comment-id:2315232742 --> @DuckyBlender commented on GitHub (Aug 28, 2024): Sorry, not familiar with I quants
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#2704
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?