github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 21:25:46 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8600] requesting support new model(maybe not new): Qwen2.5-1M #5563

New Issue
Closed
opened 2026-04-12 16:49:35 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 16:49:35 -05:00
Owner
Copy Link

Originally created by @somnifex on GitHub (Jan 27, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8600

Qwen has released a long context version of Qwen 2.5 on hugging face, hoping to add support:
https://huggingface.co/collections/Qwen/qwen25-1m-679325716327ec07860530ba

Originally created by @somnifex on GitHub (Jan 27, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8600 Qwen has released a long context version of Qwen 2.5 on hugging face, hoping to add support: https://huggingface.co/collections/Qwen/qwen25-1m-679325716327ec07860530ba
GiteaMirror added the model label 2026-04-12 16:49:35 -05:00
GiteaMirror commented 2026-04-12 16:49:37 -05:00
Author
Owner
Copy Link

@Meshwa428 commented on GitHub (Jan 27, 2025):

if you can run the qwen2.5 model, then its obvious that you can run the 1m context model. Its the same architecture. Try to convert the model to gguf and then load it using ollama and then change the value of num_ctx using this command when running ollama

/set num_ctx 1000000

and you have the model running with a million context window.

<!-- gh-comment-id:2616480356 --> @Meshwa428 commented on GitHub (Jan 27, 2025): if you can run the qwen2.5 model, then its obvious that you can run the 1m context model. Its the same architecture. Try to convert the model to gguf and then load it using ollama and then change the value of num_ctx using this command when running ollama /set num_ctx 1000000 and you have the model running with a million context window.
GiteaMirror commented 2026-04-12 16:49:37 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 5, 2026):

This model requires a custom version of vLLM:

To enhance processing accuracy and efficiency for long sequences, we have developed an advanced
inference framework based on vLLM, incorporating sparse attention and length extrapolation.

It can be imported to ollama by the usual method but:

accuracy degradation may occur for sequences exceeding 262,144 tokens.
<!-- gh-comment-id:3709522957 --> @rick-github commented on GitHub (Jan 5, 2026): This model requires a custom version of vLLM: ``` To enhance processing accuracy and efficiency for long sequences, we have developed an advanced inference framework based on vLLM, incorporating sparse attention and length extrapolation. ``` It can be imported to ollama by the [usual method](https://github.com/ollama/ollama/blob/main/docs/import.mdx#Importing-a-model-from-Safetensors-weights) but: ``` accuracy degradation may occur for sequences exceeding 262,144 tokens. ```
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 model
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#5563
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?