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 #14056] youtu/youtu-vl error loading model #55697

New Issue
Closed
opened 2026-04-29 09:36:08 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-29 09:36:08 -05:00
Owner
Copy Link

Originally created by @git9875 on GitHub (Feb 3, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14056

What is the issue?

I ran the command: ollama run youtu/youtu-vl.
When it finished downloading, it gave this error:
Error: 500 Internal Server Error: llama runner process has terminated: error loading model: error loading model hyperparameters: key not found in model: deepseek2.expert_weights_scale

Relevant log output

ollama run youtu/youtu-vl
pulling manifest
pulling 417f0d697a9a: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏ 5.2 GB
pulling 1bcb2b7a9968: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏ 893 MB
pulling 4175e009c870: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏  771 B
pulling 75357d685f23: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏   28 B
pulling 4b57630ed467: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏  108 B
pulling 1b3004b49f80: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏  574 B
verifying sha256 digest
writing manifest
success
Error: 500 Internal Server Error: llama runner process has terminated: error loading model: error loading model hyperparameters: key not found in model: deepseek2.expert_weights_scale
llama_model_load_from_file_impl: failed to load model
panic: unable to load model: C:\Users\searo\.ollama\models\blobs\sha256-417f0d697a9a7e90de283700ed444342518b0a48233e488fdc2900648cc13d92

goroutine 53 [running]:
github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc000258500, {{0xc0003c6038, 0x1, 0x1}, 0x29, 0x0, 0x0, {0xc0003c6030, 0x1, 0x2}, ...}, ...)
        github.com/ollama/ollama/runner/llamarunner/runner.go:843 +0x33f
created by github.com/ollama/ollama/runner/llamarunner.(*Server).load in goroutine 51
        github.com/ollama/ollama/runner/llamarunner/runner.go:934 +0x889

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.15.4

Originally created by @git9875 on GitHub (Feb 3, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14056 ### What is the issue? I ran the command: `ollama run youtu/youtu-vl`. When it finished downloading, it gave this error: Error: 500 Internal Server Error: llama runner process has terminated: error loading model: error loading model hyperparameters: key not found in model: deepseek2.expert_weights_scale ### Relevant log output ```shell ollama run youtu/youtu-vl pulling manifest pulling 417f0d697a9a: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏ 5.2 GB pulling 1bcb2b7a9968: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏ 893 MB pulling 4175e009c870: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏ 771 B pulling 75357d685f23: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏ 28 B pulling 4b57630ed467: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏ 108 B pulling 1b3004b49f80: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████▏ 574 B verifying sha256 digest writing manifest success Error: 500 Internal Server Error: llama runner process has terminated: error loading model: error loading model hyperparameters: key not found in model: deepseek2.expert_weights_scale llama_model_load_from_file_impl: failed to load model panic: unable to load model: C:\Users\searo\.ollama\models\blobs\sha256-417f0d697a9a7e90de283700ed444342518b0a48233e488fdc2900648cc13d92 goroutine 53 [running]: github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc000258500, {{0xc0003c6038, 0x1, 0x1}, 0x29, 0x0, 0x0, {0xc0003c6030, 0x1, 0x2}, ...}, ...) github.com/ollama/ollama/runner/llamarunner/runner.go:843 +0x33f created by github.com/ollama/ollama/runner/llamarunner.(*Server).load in goroutine 51 github.com/ollama/ollama/runner/llamarunner/runner.go:934 +0x889 ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.15.4
GiteaMirror added the bug label 2026-04-29 09:36:08 -05:00
GiteaMirror commented 2026-04-29 09:36:11 -05:00
Author
Owner
Copy Link

@ssam18 commented on GitHub (Feb 4, 2026):

I can reproduce this issue locally.

$OLLAMA_HOST=http://127.0.0.1:11434 ollama run youtu/youtu-vl "hello"
Error: llama runner process has terminated: error loading model: error loading model hyperparameters: key not found in model: deepseek2.expert_weights_scale
llama_model_load_from_file_impl: failed to load model

Issue reported on: ollama version 0.15.4
Current system version: 0.9.1
Fix status: Present in main branch but not yet released

<!-- gh-comment-id:3844854342 --> @ssam18 commented on GitHub (Feb 4, 2026): I can reproduce this issue locally. $OLLAMA_HOST=http://127.0.0.1:11434 ollama run youtu/youtu-vl "hello" Error: llama runner process has terminated: error loading model: error loading model hyperparameters: key not found in model: deepseek2.expert_weights_scale llama_model_load_from_file_impl: failed to load model Issue reported on: ollama version 0.15.4 Current system version: 0.9.1 Fix status: Present in main branch but not yet released
GiteaMirror commented 2026-04-29 09:36:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 4, 2026):

Image
<!-- gh-comment-id:3844903906 --> @rick-github commented on GitHub (Feb 4, 2026): <img width="772" height="163" alt="Image" src="https://github.com/user-attachments/assets/82f20b45-78ea-46c6-8cd6-b37575dc26f1" />
GiteaMirror commented 2026-04-29 09:36:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 4, 2026):

$ ollama run youtu/youtu-vl describe ./'Screenshot from 2026-02-04 03-32-24.png'
Added image './Screenshot from 2026-02-04 03-32-24.png'
This image shows a screenshot of a software package page, likely from a 
Linux package repository (such as Linuxbrew or a similar system), for a 
tool called **youtu / youtu-vl**.

Here’s a breakdown of what’s shown:

---

### 📌 Package Name:
**youtu / youtu-vl**

This is likely a lightweight version of the Youtu-LM (YouTube Large Model) 
developed by Tencent, optimized for visual understanding tasks.

---

### 📊 Statistics:
- **76 Downloads** — Indicates how many times this package has been 
downloaded.
- **Updated 6 days ago** — Shows when the latest version was released or 
updated.

---

### 📝 Description:
> *Youtu-VL: a lightweight 4B VLM built on Youtu-LM, pioneering VLUAS to 
improve visual perception and multimodal understanding. Requires Ollama 
v0.15.5-rc1 or higher*

- **Youtu-VL** stands for YouTube Large Model — a vision-language model 
(VLM) designed to understand and generate text based on visual inputs.
- It’s built on top of the Youtu-LM foundation, which is known for its 
multimodal capabilities.
- The description highlights its innovation in **VLUAS** (Vision-Language 
Understanding and Analysis), aiming to enhance both visual perception and 
multimodal understanding.
- **Dependency**: Requires **Ollama v0.15.5-rc1 or higher** — Ollama is a 
tool for running large language models locally on Linux systems.

---

### 🟦 Tag:
**vision** — This tag categorizes the package under the “vision” domain, 
indicating its relevance to computer vision and visual understanding 
tasks.

---

### 🔴 Highlighted Section:
The red box draws attention to the **dependency requirement**:  
> *Requires Ollama v0.15.5-rc1 or higher*

This is important for users who want to install or run Youtu-VL — they 
must ensure their Ollama version meets or exceeds this threshold.

---

### 💡 Summary:
This is a lightweight (4B parameter) vision-language model built on 
Tencent’s Youtu-LM, designed for visual perception and multimodal 
understanding. It requires a specific version of Ollama to run locally. 
The package is categorized under “vision” and has been recently updated.

---

✅ **Use Case**: Ideal for developers or researchers working on visual 
question answering, image captioning, or multimodal AI applications that 
need to integrate with Youtu’s vision-language capabilities.

Let me know if you want help installing or running it!
<!-- gh-comment-id:3844914613 --> @rick-github commented on GitHub (Feb 4, 2026): ```console $ ollama run youtu/youtu-vl describe ./'Screenshot from 2026-02-04 03-32-24.png' Added image './Screenshot from 2026-02-04 03-32-24.png' This image shows a screenshot of a software package page, likely from a Linux package repository (such as Linuxbrew or a similar system), for a tool called **youtu / youtu-vl**. Here’s a breakdown of what’s shown: --- ### 📌 Package Name: **youtu / youtu-vl** This is likely a lightweight version of the Youtu-LM (YouTube Large Model) developed by Tencent, optimized for visual understanding tasks. --- ### 📊 Statistics: - **76 Downloads** — Indicates how many times this package has been downloaded. - **Updated 6 days ago** — Shows when the latest version was released or updated. --- ### 📝 Description: > *Youtu-VL: a lightweight 4B VLM built on Youtu-LM, pioneering VLUAS to improve visual perception and multimodal understanding. Requires Ollama v0.15.5-rc1 or higher* - **Youtu-VL** stands for YouTube Large Model — a vision-language model (VLM) designed to understand and generate text based on visual inputs. - It’s built on top of the Youtu-LM foundation, which is known for its multimodal capabilities. - The description highlights its innovation in **VLUAS** (Vision-Language Understanding and Analysis), aiming to enhance both visual perception and multimodal understanding. - **Dependency**: Requires **Ollama v0.15.5-rc1 or higher** — Ollama is a tool for running large language models locally on Linux systems. --- ### 🟦 Tag: **vision** — This tag categorizes the package under the “vision” domain, indicating its relevance to computer vision and visual understanding tasks. --- ### 🔴 Highlighted Section: The red box draws attention to the **dependency requirement**: > *Requires Ollama v0.15.5-rc1 or higher* This is important for users who want to install or run Youtu-VL — they must ensure their Ollama version meets or exceeds this threshold. --- ### 💡 Summary: This is a lightweight (4B parameter) vision-language model built on Tencent’s Youtu-LM, designed for visual perception and multimodal understanding. It requires a specific version of Ollama to run locally. The package is categorized under “vision” and has been recently updated. --- ✅ **Use Case**: Ideal for developers or researchers working on visual question answering, image captioning, or multimodal AI applications that need to integrate with Youtu’s vision-language capabilities. Let me know if you want help installing or running it! ```
GiteaMirror commented 2026-04-29 09:36:12 -05:00
Author
Owner
Copy Link

@git9875 commented on GitHub (Feb 4, 2026):

I missed the version detail. I didn't think of checking the version since I get automatic updates. The releases on the Ollama Github page still shows v0.15.4 though.

<!-- gh-comment-id:3844943949 --> @git9875 commented on GitHub (Feb 4, 2026): I missed the version detail. I didn't think of checking the version since I get automatic updates. The releases on the Ollama Github page still shows v0.15.4 though.
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#55697
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?