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 #3570] More details in Model Info #48714

New Issue
Closed
opened 2026-04-28 09:07:42 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 09:07:42 -05:00
Owner
Copy Link

Originally created by @corani on GitHub (Apr 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3570

Originally assigned to: @royjhan on GitHub.

What are you trying to do?

Would it be possible to expose more information in the model info (https://github.com/ollama/ollama/blob/main/docs/api.md#show-model-information) API, such as the context length, embedding length etc.? Basically, the more the merrier 😄

This would be useful to provide additional information to the user when building a service that wraps Ollama.

How should we solve this?

No response

What is the impact of not solving this?

No response

Anything else?

No response

Originally created by @corani on GitHub (Apr 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3570 Originally assigned to: @royjhan on GitHub. ### What are you trying to do? Would it be possible to expose more information in the model info (https://github.com/ollama/ollama/blob/main/docs/api.md#show-model-information) API, such as the context length, embedding length etc.? Basically, the more the merrier 😄 This would be useful to provide additional information to the user when building a service that wraps Ollama. ### How should we solve this? _No response_ ### What is the impact of not solving this? _No response_ ### Anything else? _No response_
GiteaMirror added the feature request label 2026-04-28 09:07:42 -05:00
GiteaMirror commented 2026-04-28 09:07:45 -05:00
Author
Owner
Copy Link

@guyvdb commented on GitHub (Apr 10, 2024):

Would it be possible to determine if the model file is able to perform completion/embedding? If I am looping through all the models obtained via GET /api/tags, and am trying to preform some inference on the model, I (obviously) get an error performing inference on embedding model.

Perhaps /api/tags or /api/show could contain information on which /api/endpoints are usable with the model.

<!-- gh-comment-id:2047237724 --> @guyvdb commented on GitHub (Apr 10, 2024): Would it be possible to determine if the model file is able to perform completion/embedding? If I am looping through all the models obtained via GET /api/tags, and am trying to preform some inference on the model, I (obviously) get an error performing inference on embedding model. Perhaps /api/tags or /api/show could contain information on which /api/endpoints are usable with the model.
GiteaMirror commented 2026-04-28 09:07:47 -05:00
Author
Owner
Copy Link

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

I second this request. Currently we get data like this from the /api/tags and /api/show endpoints (show data has been put in the "meta" key):

{"name"=>"llama3:latest",
  "model"=>"llama3:latest",
  "modified_at"=>"2024-05-07T11:51:37.263117-07:00",
  "size"=>4661224578,
  "digest"=>"a6990ed6be412c6a217614b0ec8e9cd6800a743d5dd7e1d7fbe9df09e61d5615",
  "meta"=>
   {"parent_model"=>"",
    "format"=>"gguf",
    "family"=>"llama",
    "families"=>["llama"],
    "parameter_size"=>"8B",
    "quantization_level"=>"Q4_0"},
  "id"=>"llama3:latest"},
 {"name"=>"mistral:instruct",
  "model"=>"mistral:instruct",
  "modified_at"=>"2024-05-02T10:27:48.766655-07:00",
  "size"=>4109865159,
  "digest"=>"61e88e884507ba5e06c49b40e6226884b2a16e872382c2b44a42f2d119d804a5",
  "meta"=>
   {"parent_model"=>"",
    "format"=>"gguf",
    "family"=>"llama",
    "families"=>["llama"],
    "parameter_size"=>"7B",
    "quantization_level"=>"Q4_0"},
  "id"=>"mistral:instruct"}

this is useful but what would be even more useful is to know the following:

  • maximum context window size
  • training context window
  • whether generation and/or embedding is supported (maybe this is always true?)
  • number of dimensions for embeddings (if supported)

The dimensions of the embedding is particularly important for a wrapper that plans to use the /api/embeddings output for a vector database which has a fixed vector size (for example, a postgres database with the pg_vector plugin, where the vector column was created with a specific dimensionality, e.g. 768), and attempting to store the wrong number of dimensions will result in an error. Ideally we would want to validate the model that we plan to use for embeddings to ensure the dimensionality matches.

Additionally its difficult currently to get a definitive answer as to the context size of a given model without looking up the model on hugging face etc. It would be extremely helpful if that info could be provided in the /api/show output for the model.

<!-- gh-comment-id:2105284515 --> @moracca commented on GitHub (May 10, 2024): I second this request. Currently we get data like this from the /api/tags and /api/show endpoints (show data has been put in the "meta" key): ``` {"name"=>"llama3:latest", "model"=>"llama3:latest", "modified_at"=>"2024-05-07T11:51:37.263117-07:00", "size"=>4661224578, "digest"=>"a6990ed6be412c6a217614b0ec8e9cd6800a743d5dd7e1d7fbe9df09e61d5615", "meta"=> {"parent_model"=>"", "format"=>"gguf", "family"=>"llama", "families"=>["llama"], "parameter_size"=>"8B", "quantization_level"=>"Q4_0"}, "id"=>"llama3:latest"}, {"name"=>"mistral:instruct", "model"=>"mistral:instruct", "modified_at"=>"2024-05-02T10:27:48.766655-07:00", "size"=>4109865159, "digest"=>"61e88e884507ba5e06c49b40e6226884b2a16e872382c2b44a42f2d119d804a5", "meta"=> {"parent_model"=>"", "format"=>"gguf", "family"=>"llama", "families"=>["llama"], "parameter_size"=>"7B", "quantization_level"=>"Q4_0"}, "id"=>"mistral:instruct"} ``` this is useful but what would be even more useful is to know the following: - maximum context window size - training context window - whether generation and/or embedding is supported (maybe this is always true?) - number of dimensions for embeddings (if supported) The dimensions of the embedding is particularly important for a wrapper that plans to use the /api/embeddings output for a vector database which has a fixed vector size (for example, a postgres database with the pg_vector plugin, where the vector column was created with a specific dimensionality, e.g. 768), and attempting to store the wrong number of dimensions will result in an error. Ideally we would want to validate the model that we plan to use for embeddings to ensure the dimensionality matches. Additionally its difficult currently to get a definitive answer as to the context size of a given model without looking up the model on hugging face etc. It would be extremely helpful if that info could be provided in the /api/show output for the model.
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 feature request
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#48714
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?