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 #3272] Error: exception create_tensor: tensor 'output.weight' not found #48528

New Issue
Closed
opened 2026-04-28 08:47:19 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 08:47:19 -05:00
Owner
Copy Link

Originally created by @GhadaJouini on GitHub (Mar 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3272

What is the issue?

I'm trying to add a custom model in ollama but am encountering this error. Is it possible that the model quantization is not correct ?

Error: exception create_tensor: tensor 'output.weight' not found

Quantized model: https://huggingface.co/MaziyarPanahi/zephyr-7b-gemma-v0.1-GGUF

I’m under ollama version : 0.1.29

Os distribution:

PRETTY_NAME="Ubuntu 22.04.4 LTS" NAME="Ubuntu" VERSION_ID="22.04" VERSION="22.04.4 LTS (Jammy Jellyfish)" VERSION_CODENAME=jammy ID=ubuntu ID_LIKE=debian

OllamaError

OSDistribution

What did you expect to see?

The model should run correctly

Steps to reproduce

Step 1: installing git lfs
Step2 : Using the HuggingFaceModelDownloader to download the model from huggingFace
Step 3: Create the Modelfile
Step 4: Create the model using the command: ollama create "zephyr-7b-gemma-v0.1.Q6_0" -f Modelfile
Step 5: Run the model using the command: ollama run zephyr-7b-gemma-v0.1.Q6_0:latest

Are there any recent changes that introduced the issue?

Modelfile:

FROM ./zephyr-7b-gemma-v0.1.Q6_K.gguf

TEMPLATE "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"

OS

No response

Architecture

No response

Platform

No response

Ollama version

No response

GPU

No GPU

GPU info

No response

CPU

No response

Other software

No response

Originally created by @GhadaJouini on GitHub (Mar 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3272 ### What is the issue? I'm trying to add a custom model in ollama but am encountering this error. Is it possible that the model quantization is not correct ? **Error: exception create_tensor: tensor 'output.weight' not found** Quantized model: https://huggingface.co/MaziyarPanahi/zephyr-7b-gemma-v0.1-GGUF I’m under ollama version : **0.1.29** **Os distribution:** PRETTY_NAME="Ubuntu 22.04.4 LTS" NAME="Ubuntu" VERSION_ID="22.04" VERSION="22.04.4 LTS (Jammy Jellyfish)" VERSION_CODENAME=jammy ID=ubuntu ID_LIKE=debian ![OllamaError](https://github.com/ollama/ollama/assets/32711189/63fcd1a1-8f52-4ece-806e-60fda31de382) ![OSDistribution](https://github.com/ollama/ollama/assets/32711189/f3dbd0c3-b617-4ebe-9a6f-692fa904480c) ### What did you expect to see? The model should run correctly ### Steps to reproduce Step 1: installing git lfs Step2 : Using the [HuggingFaceModelDownloader](https://github.com/bodaay/HuggingFaceModelDownloader) to download the model from huggingFace Step 3: Create the Modelfile Step 4: Create the model using the command: **ollama create "zephyr-7b-gemma-v0.1.Q6_0" -f Modelfile** Step 5: Run the model using the command: **ollama run zephyr-7b-gemma-v0.1.Q6_0:latest** ### Are there any recent changes that introduced the issue? Modelfile: FROM ./zephyr-7b-gemma-v0.1.Q6_K.gguf TEMPLATE "<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant" ### OS _No response_ ### Architecture _No response_ ### Platform _No response_ ### Ollama version _No response_ ### GPU No GPU ### GPU info _No response_ ### CPU _No response_ ### Other software _No response_
GiteaMirror added the bug label 2026-04-28 08:47:19 -05:00
GiteaMirror commented 2026-04-28 08:47:20 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Apr 15, 2024):

Hi there, this should be fixed now.

<!-- gh-comment-id:2057679685 --> @jmorganca commented on GitHub (Apr 15, 2024): Hi there, this should be fixed now.
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#48528
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?