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 #3638] Error: exception error loading model architecture: unknown model architecture: '' #2243

New Issue
Closed
opened 2026-04-12 12:31:04 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 12:31:04 -05:00
Owner
Copy Link

Originally created by @anubissbe on GitHub (Apr 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3638

What is the issue?

The modelfile cannot get loaded after the model creation

What did you expect to see?

A working chat interface

Steps to reproduce

drwho@jarvis:/opt/models/aya-101-GGUF$ ollama create aya -f Modelfile
transferring model data
creating model layer
creating system layer
creating parameters layer
creating config layer
using already created layer sha256:dcf5054951605dfee65396ef3c625c09539c5f605256989bf9e605e9727a00d8
writing layer sha256:d8ba2f9a17b3bbdeb5690efaa409b3fcb0b56296a777c7a69c78aa33bbddf182
writing layer sha256:d8f76500493b5c8d3ca7146cefe969f5a3a7ed1a36dffdfb06feb49089d19d7c
writing manifest
success
drwho@jarvis:/opt/models/aya-101-GGUF$ ollama run aya
Error: exception error loading model architecture: unknown model architecture: ''
drwho@jarvis:/opt/models/aya-101-GGUF$ cat Modelfile
FROM ./aya-101.Q6_K.gguf

set the temperature to 1 [higher is more creative, lower is more coherent]

PARAMETER temperature 1

set the system message

SYSTEM ""
drwho@jarvis:/opt/models/aya-101-GGUF$ ls -la
total 110839576
drwxrwxr-x 3 drwho drwho 4096 Apr 14 14:17 .
drwxr-xr-x 4 drwho users 4096 Apr 14 12:37 ..
-rw-rw-r-- 1 drwho drwho 4241619232 Apr 14 13:25 aya-101.Q2_K.gguf
-rw-rw-r-- 1 drwho drwho 5553862944 Apr 14 13:24 aya-101.Q3_K.gguf
-rw-rw-r-- 1 drwho drwho 7269859872 Apr 14 13:26 aya-101.Q4_0.gguf
-rw-rw-r-- 1 drwho drwho 8077394720 Apr 14 13:04 aya-101.Q4_1.gguf
-rw-rw-r-- 1 drwho drwho 7269873952 Apr 14 13:26 aya-101.Q4_K.gguf
-rw-rw-r-- 1 drwho drwho 8884929568 Apr 14 13:07 aya-101.Q5_0.gguf
-rw-rw-r-- 1 drwho drwho 9692464416 Apr 14 13:13 aya-101.Q5_1.gguf
-rw-rw-r-- 1 drwho drwho 8884943136 Apr 14 13:07 aya-101.Q5_K.gguf
-rw-rw-r-- 1 drwho drwho 10600954144 Apr 14 13:13 aya-101.Q6_K.gguf
-rw-rw-r-- 1 drwho drwho 13730138656 Apr 14 13:25 aya-101.Q8_0.gguf
-rw-rw-r-- 1 drwho drwho 14537673504 Apr 14 13:24 aya-101.Q8_1.gguf
-rw-rw-r-- 1 drwho drwho 14739568928 Apr 14 13:25 aya-101.Q8_K.gguf
-rw-rw-r-- 1 drwho drwho 761 Apr 14 14:07 config.json
drwxrwxr-x 9 drwho drwho 4096 Apr 14 13:37 .git
-rw-rw-r-- 1 drwho drwho 2218 Apr 14 12:37 .gitattributes
-rw-rw-r-- 1 drwho drwho 162 Apr 14 14:17 Modelfile
-rw-rw-r-- 1 drwho drwho 2270 Apr 14 12:37 README.md
-rw-rw-r-- 1 drwho drwho 833 Apr 14 12:37 tokenizer_config.json
-rw-rw-r-- 1 drwho drwho 16330562 Apr 14 13:13 tokenizer.json

Are there any recent changes that introduced the issue?

No response

OS

Linux

Architecture

amd64

Platform

No response

Ollama version

No response

GPU

Nvidia

GPU info

V100-16GB

CPU

Intel

Other software

Xeon-Gold

Originally created by @anubissbe on GitHub (Apr 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3638 ### What is the issue? The modelfile cannot get loaded after the model creation ### What did you expect to see? A working chat interface ### Steps to reproduce drwho@jarvis:/opt/models/aya-101-GGUF$ ollama create aya -f Modelfile transferring model data creating model layer creating system layer creating parameters layer creating config layer using already created layer sha256:dcf5054951605dfee65396ef3c625c09539c5f605256989bf9e605e9727a00d8 writing layer sha256:d8ba2f9a17b3bbdeb5690efaa409b3fcb0b56296a777c7a69c78aa33bbddf182 writing layer sha256:d8f76500493b5c8d3ca7146cefe969f5a3a7ed1a36dffdfb06feb49089d19d7c writing manifest success drwho@jarvis:/opt/models/aya-101-GGUF$ ollama run aya Error: exception error loading model architecture: unknown model architecture: '' drwho@jarvis:/opt/models/aya-101-GGUF$ cat Modelfile FROM ./aya-101.Q6_K.gguf # set the temperature to 1 [higher is more creative, lower is more coherent] PARAMETER temperature 1 # set the system message SYSTEM "" drwho@jarvis:/opt/models/aya-101-GGUF$ ls -la total 110839576 drwxrwxr-x 3 drwho drwho 4096 Apr 14 14:17 . drwxr-xr-x 4 drwho users 4096 Apr 14 12:37 .. -rw-rw-r-- 1 drwho drwho 4241619232 Apr 14 13:25 aya-101.Q2_K.gguf -rw-rw-r-- 1 drwho drwho 5553862944 Apr 14 13:24 aya-101.Q3_K.gguf -rw-rw-r-- 1 drwho drwho 7269859872 Apr 14 13:26 aya-101.Q4_0.gguf -rw-rw-r-- 1 drwho drwho 8077394720 Apr 14 13:04 aya-101.Q4_1.gguf -rw-rw-r-- 1 drwho drwho 7269873952 Apr 14 13:26 aya-101.Q4_K.gguf -rw-rw-r-- 1 drwho drwho 8884929568 Apr 14 13:07 aya-101.Q5_0.gguf -rw-rw-r-- 1 drwho drwho 9692464416 Apr 14 13:13 aya-101.Q5_1.gguf -rw-rw-r-- 1 drwho drwho 8884943136 Apr 14 13:07 aya-101.Q5_K.gguf -rw-rw-r-- 1 drwho drwho 10600954144 Apr 14 13:13 aya-101.Q6_K.gguf -rw-rw-r-- 1 drwho drwho 13730138656 Apr 14 13:25 aya-101.Q8_0.gguf -rw-rw-r-- 1 drwho drwho 14537673504 Apr 14 13:24 aya-101.Q8_1.gguf -rw-rw-r-- 1 drwho drwho 14739568928 Apr 14 13:25 aya-101.Q8_K.gguf -rw-rw-r-- 1 drwho drwho 761 Apr 14 14:07 config.json drwxrwxr-x 9 drwho drwho 4096 Apr 14 13:37 .git -rw-rw-r-- 1 drwho drwho 2218 Apr 14 12:37 .gitattributes -rw-rw-r-- 1 drwho drwho 162 Apr 14 14:17 Modelfile -rw-rw-r-- 1 drwho drwho 2270 Apr 14 12:37 README.md -rw-rw-r-- 1 drwho drwho 833 Apr 14 12:37 tokenizer_config.json -rw-rw-r-- 1 drwho drwho 16330562 Apr 14 13:13 tokenizer.json ### Are there any recent changes that introduced the issue? _No response_ ### OS Linux ### Architecture amd64 ### Platform _No response_ ### Ollama version _No response_ ### GPU Nvidia ### GPU info V100-16GB ### CPU Intel ### Other software Xeon-Gold
GiteaMirror added the bug label 2026-04-12 12:31:04 -05:00
GiteaMirror commented 2026-04-12 12:31:05 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Apr 17, 2024):

Hi there, Ollama doesn't support the T5 architecture yet - however feel free to create a model request issue so we can work on supporting it :)

<!-- gh-comment-id:2060138776 --> @jmorganca commented on GitHub (Apr 17, 2024): Hi there, Ollama doesn't support the T5 architecture yet - however feel free to create a model request issue so we can work on supporting it :)
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#2243
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?