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

[GH-ISSUE #4217] how to load adapter #64665

New Issue
Closed
opened 2026-05-03 18:28:00 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 18:28:00 -05:00
Owner
Copy Link

Originally created by @taozhiyuai on GitHub (May 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4217

What is the issue?

how to load adapter

modelfile is the following:

FROM ./sha256-b6f248eff2d0c4f85d2f6369a27d99fc75686d67314a0b5d35a93c5aee5dcb14
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 num_ctx 1040000
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
ADAPTER ./adapter_model.safetensors
ERROR info is :
'taozhiyu@603e5f4a42f1 Llama-3-70B-Gradient-1048k-adapter % ollama create llama3:70b-instruct-1mb-q8_0 -f modelfile
transferring model data
creating model layer
creating template layer
creating adapter layer
Error: invalid file magic'

adapter is from https://hf-mirror.com/cognitivecomputations/Llama-3-70B-Gradient-1048k-adapter

anyone can help for this issue?

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.32

Originally created by @taozhiyuai on GitHub (May 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4217 ### What is the issue? how to load adapter modelfile is the following: FROM ./sha256-b6f248eff2d0c4f85d2f6369a27d99fc75686d67314a0b5d35a93c5aee5dcb14 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 num_ctx 1040000 PARAMETER stop "<|start_header_id|>" PARAMETER stop "<|end_header_id|>" PARAMETER stop "<|eot_id|>" ADAPTER ./adapter_model.safetensors ERROR info is : 'taozhiyu@603e5f4a42f1 Llama-3-70B-Gradient-1048k-adapter % ollama create llama3:70b-instruct-1mb-q8_0 -f modelfile transferring model data creating model layer creating template layer creating adapter layer Error: invalid file magic' adapter is from https://hf-mirror.com/cognitivecomputations/Llama-3-70B-Gradient-1048k-adapter anyone can help for this issue? ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-05-03 18:28:00 -05:00
GiteaMirror commented 2026-05-03 18:28:03 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 7, 2024):

Hi @taozhiyuai adapters must be GGUF files at the moment, this is something we'll improve in the future!

<!-- gh-comment-id:2098880982 --> @jmorganca commented on GitHub (May 7, 2024): Hi @taozhiyuai adapters must be GGUF files at the moment, this is something we'll improve in the future!
GiteaMirror commented 2026-05-03 18:28:03 -05:00
Author
Owner
Copy Link

@taozhiyuai commented on GitHub (May 10, 2024):

Hi @taozhiyuai adapters must be GGUF files at the moment, this is something we'll improve in the future!

so I just convert a lora on HF by llama.cpp to GGUF, then I can attach it on ollama model file? @jmorganca

<!-- gh-comment-id:2103787803 --> @taozhiyuai commented on GitHub (May 10, 2024): > Hi @taozhiyuai adapters must be GGUF files at the moment, this is something we'll improve in the future! so I just convert a lora on HF by llama.cpp to GGUF, then I can attach it on ollama model file? @jmorganca
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 bug
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#64665
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?