github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13571] KaLM-Embedding/KaLM-Embedding-Gemma3-12B-2511 can not generate embedding #55449

New Issue
Closed
opened 2026-04-29 09:14:39 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-29 09:14:39 -05:00
Owner
Copy Link

Originally created by @Genuifx on GitHub (Dec 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13571

KaLM-Embedding/KaLM-Embedding-Gemma3-12B-2511 is recognized as chat model.

curl http://localhost:11434/api/embed -d '{
  "model": "KaLM-Embedding/KaLM-Embedding-Gemma3-12B-2511",
  "input": "Why is the sky blue?"
}'
{"error":"this model does not support embeddings"}%
Originally created by @Genuifx on GitHub (Dec 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13571 KaLM-Embedding/KaLM-Embedding-Gemma3-12B-2511 is recognized as chat model. ``` curl http://localhost:11434/api/embed -d '{ "model": "KaLM-Embedding/KaLM-Embedding-Gemma3-12B-2511", "input": "Why is the sky blue?" }' {"error":"this model does not support embeddings"}% ```
GiteaMirror commented 2026-04-29 09:14:39 -05:00
Author
Owner
Copy Link

@anumukul commented on GitHub (Dec 26, 2025):

Hi, I’d like to take this issue and can deliver a fix within 24 hours.
I’ve worked on similar projects before and have relevant experience, so I should be able to handle this efficiently.

<!-- gh-comment-id:3693470959 --> @anumukul commented on GitHub (Dec 26, 2025): Hi, I’d like to take this issue and can deliver a fix within 24 hours. I’ve worked on similar projects before and have relevant experience, so I should be able to handle this efficiently.
GiteaMirror commented 2026-04-29 09:14:40 -05:00
Author
Owner
Copy Link

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

The model is missing metadata that identifies it as an embedding model:

$ ollama show KaLM-Embedding/KaLM-Embedding-Gemma3-12B-2511 
  Model
    architecture        gemma3    
    parameters          11.8B     
    context length      131072    
    embedding length    3840      
    quantization        BF16      

  Capabilities
    completion

I imported the original model from https://huggingface.co/tencent/KaLM-Embedding-Gemma3-12B-2511 and uploaded it to the ollama library at https://ollama.com/frob/KaLM-Embedding-Gemma3-12B-2511.

$ ollama show frob/KaLM-Embedding-Gemma3-12B-2511 
  Model
    architecture        gemma-embedding    
    parameters          11.8B              
    context length      131072             
    embedding length    3840               
    quantization        F16                

  Capabilities
    embedding    

$ curl -s http://localhost:11434/api/embed -d '{
  "model": "frob/KaLM-Embedding-Gemma3-12B-2511",
  "input": "Why is the sky blue?"
}' | jq -c '.embeddings[0]|.[:3] + ["..."] + .[-3:]'
[0.022915034,-0.016313432,-0.08286263,"...",0.0087134335,0.0029289108,0.012182114]
<!-- gh-comment-id:3707660107 --> @rick-github commented on GitHub (Jan 4, 2026): The model is missing metadata that identifies it as an embedding model: ```console $ ollama show KaLM-Embedding/KaLM-Embedding-Gemma3-12B-2511 Model architecture gemma3 parameters 11.8B context length 131072 embedding length 3840 quantization BF16 Capabilities completion ``` I imported the original model from https://huggingface.co/tencent/KaLM-Embedding-Gemma3-12B-2511 and uploaded it to the ollama library at https://ollama.com/frob/KaLM-Embedding-Gemma3-12B-2511. ```console $ ollama show frob/KaLM-Embedding-Gemma3-12B-2511 Model architecture gemma-embedding parameters 11.8B context length 131072 embedding length 3840 quantization F16 Capabilities embedding $ curl -s http://localhost:11434/api/embed -d '{ "model": "frob/KaLM-Embedding-Gemma3-12B-2511", "input": "Why is the sky blue?" }' | jq -c '.embeddings[0]|.[:3] + ["..."] + .[-3:]' [0.022915034,-0.016313432,-0.08286263,"...",0.0087134335,0.0029289108,0.012182114] ```
GiteaMirror commented 2026-04-29 09:14:40 -05:00
Author
Owner
Copy Link

@ashunaveed commented on GitHub (Jan 4, 2026):

how to convert huggingface based safetensors models to ollama models to be used for embeddings usage with the embedding dimension provided by the model..

<!-- gh-comment-id:3708365206 --> @ashunaveed commented on GitHub (Jan 4, 2026): how to convert huggingface based safetensors models to ollama models to be used for embeddings usage with the embedding dimension provided by the model..
GiteaMirror commented 2026-04-29 09:14:40 -05:00
Author
Owner
Copy Link

@tatankam commented on GitHub (Mar 2, 2026):

For me it doesn't work.

I obtain:

curl http://localhost:11434/api/embeddings   -d '{
    "model": "frob/KaLM-Embedding-Gemma3-12B-2511",
    "prompt": "Ciao, come va oggi?"
  }'
{"error":"llama runner process has terminated: GGML_ASSERT(ggml_nbytes(src0) \u003c= INT_MAX) failed"}
<!-- gh-comment-id:3983892063 --> @tatankam commented on GitHub (Mar 2, 2026): For me it doesn't work. I obtain: ``` curl http://localhost:11434/api/embeddings -d '{ "model": "frob/KaLM-Embedding-Gemma3-12B-2511", "prompt": "Ciao, come va oggi?" }' {"error":"llama runner process has terminated: GGML_ASSERT(ggml_nbytes(src0) \u003c= INT_MAX) failed"} ```
GiteaMirror commented 2026-04-29 09:14:40 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 2, 2026):

Set OLLAMA_CONTEXT_LENGTH=8192 in the server environment.

<!-- gh-comment-id:3986154155 --> @rick-github commented on GitHub (Mar 2, 2026): Set `OLLAMA_CONTEXT_LENGTH=8192` in the server environment.
GiteaMirror commented 2026-04-29 09:14:41 -05:00
Author
Owner
Copy Link

@tatankam commented on GitHub (Mar 3, 2026):

Hi,
on my ollama server that is bigger:
Environment=OLLAMA_CONTEXT_LENGTH=32768

but it doesn't work

<!-- gh-comment-id:3989240158 --> @tatankam commented on GitHub (Mar 3, 2026): Hi, on my ollama server that is bigger: Environment=OLLAMA_CONTEXT_LENGTH=32768 but it doesn't work
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
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#55449
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?