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 #6415] Feature Request: Adding FalconMamba 7B Instruct in ollama #29792

New Issue
Open
opened 2026-04-22 09:02:05 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-22 09:02:05 -05:00
Owner
Copy Link

Originally created by @younesbelkada on GitHub (Aug 19, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6415

FalconMamba is being added here in llama.cpp: https://github.com/ggerganov/llama.cpp/pull/9074 it would be nice to have the first SSM-based LLM on ollama !
Instruct weights: https://huggingface.co/tiiuae/falcon-mamba-7b-instruct
GGUF weights: https://huggingface.co/collections/tiiuae/falconmamba-7b-66b9a580324dd1598b0f6d4a

Originally created by @younesbelkada on GitHub (Aug 19, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6415 FalconMamba is being added here in llama.cpp: https://github.com/ggerganov/llama.cpp/pull/9074 it would be nice to have the first SSM-based LLM on ollama ! Instruct weights: https://huggingface.co/tiiuae/falcon-mamba-7b-instruct GGUF weights: https://huggingface.co/collections/tiiuae/falconmamba-7b-66b9a580324dd1598b0f6d4a
GiteaMirror added the model label 2026-04-22 09:02:05 -05:00
GiteaMirror commented 2026-04-22 09:02:07 -05:00
Author
Owner
Copy Link

@younesbelkada commented on GitHub (Aug 26, 2024):

cc @mxyng @jmorganca

<!-- gh-comment-id:2309379390 --> @younesbelkada commented on GitHub (Aug 26, 2024): cc @mxyng @jmorganca
GiteaMirror commented 2026-04-22 09:02:08 -05:00
Author
Owner
Copy Link

@hg0428 commented on GitHub (Oct 1, 2024):

Any progress on this?

<!-- gh-comment-id:2384672580 --> @hg0428 commented on GitHub (Oct 1, 2024): Any progress on this?
GiteaMirror commented 2026-04-22 09:02:09 -05:00
Author
Owner
Copy Link

@hg0428 commented on GitHub (Oct 8, 2024):

Screenshot_2024-10-07_at_21 18 24 I am uploading this model now. However, there seems to be a quality issue. I'm not sure what the problem is, but I don't think it is supposed to do this.
<!-- gh-comment-id:2398401931 --> @hg0428 commented on GitHub (Oct 8, 2024): <img width="1263" alt="Screenshot_2024-10-07_at_21 18 24" src="https://github.com/user-attachments/assets/a1b28749-de73-45f3-aaab-8f3c15154c92"> I am uploading this model now. However, there seems to be a quality issue. I'm not sure what the problem is, but I don't think it is supposed to do this.
GiteaMirror commented 2026-04-22 09:02:09 -05:00
Author
Owner
Copy Link

@Lodest4r commented on GitHub (Oct 12, 2024):

@hg0428 I'm trying to use the model you uploaded but keep getting "Error: llama runner process has terminated: GGML_ASSERT(ggml_is_contiguous(src0)) failed".

<!-- gh-comment-id:2408582654 --> @Lodest4r commented on GitHub (Oct 12, 2024): @hg0428 I'm trying to use the model you uploaded but keep getting "Error: llama runner process has terminated: GGML_ASSERT(ggml_is_contiguous(src0)) failed".
GiteaMirror commented 2026-04-22 09:02:10 -05:00
Author
Owner
Copy Link

@hg0428 commented on GitHub (Oct 13, 2024):

Screenshot_2024-10-07_at_21 18 24 I am uploading this model now. However, there seems to be a quality issue. I'm not sure what the problem is, but I don't think it is supposed to do this.

The quality issue was fixed. It was just those specific parameters.

<!-- gh-comment-id:2408780089 --> @hg0428 commented on GitHub (Oct 13, 2024): > <img alt="Screenshot_2024-10-07_at_21 18 24" width="1263" src="https://private-user-images.githubusercontent.com/45984899/374373941-a1b28749-de73-45f3-aaab-8f3c15154c92.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.YCaRUaUFPsGltHcHLvWXJ6LMdwisps0rR3NajCgGqzo"> I am uploading this model now. However, there seems to be a quality issue. I'm not sure what the problem is, but I don't think it is supposed to do this. The quality issue was fixed. It was just those specific parameters.
GiteaMirror commented 2026-04-22 09:02:10 -05:00
Author
Owner
Copy Link

@hg0428 commented on GitHub (Oct 13, 2024):

@hg0428 I'm trying to use the model you uploaded but keep getting "Error: llama runner process has terminated: GGML_ASSERT(ggml_is_contiguous(src0)) failed".

What command did you run that gave you that error? What platform are you on? It seems to work fine on Mac (Apple Silicon). Perhaps it is a problem with Llama.cpp?

<!-- gh-comment-id:2408780297 --> @hg0428 commented on GitHub (Oct 13, 2024): > @hg0428 I'm trying to use the model you uploaded but keep getting "Error: llama runner process has terminated: GGML_ASSERT(ggml_is_contiguous(src0)) failed". What command did you run that gave you that error? What platform are you on? It seems to work fine on Mac (Apple Silicon). Perhaps it is a problem with Llama.cpp?
GiteaMirror commented 2026-04-22 09:02:11 -05:00
Author
Owner
Copy Link

@gabe-l-hart commented on GitHub (Jul 14, 2025):

Hi @younesbelkada! Now that we've got your PR for FalconMamba and Falcon H1 merged in llama.cpp, along with Granite4, I've got a draft bumping llama.cpp here to provide support. As usual, there are many conflated changes, so any additional help testing new or old models with the updated code would be much appreciated.

<!-- gh-comment-id:3069922137 --> @gabe-l-hart commented on GitHub (Jul 14, 2025): Hi @younesbelkada! Now that we've got your PR for FalconMamba and Falcon H1 merged in `llama.cpp`, along with Granite4, I've got [a draft](https://github.com/ollama/ollama/pull/11195) bumping `llama.cpp` here to provide support. As usual, there are many conflated changes, so any additional help testing new or old models with the updated code would be much appreciated.
GiteaMirror commented 2026-04-22 09:02:11 -05:00
Author
Owner
Copy Link

@younesbelkada commented on GitHub (Jul 14, 2025):

Thank you @gabe-l-hart for your awesome work ! will test that out and loop back on the PR directly !

<!-- gh-comment-id:3069974411 --> @younesbelkada commented on GitHub (Jul 14, 2025): Thank you @gabe-l-hart for your awesome work ! will test that out and loop back on the PR directly !
GiteaMirror commented 2026-04-22 09:02:12 -05:00
Author
Owner
Copy Link

@gabe-l-hart commented on GitHub (Jul 14, 2025):

Awesome, much appreciated!

<!-- gh-comment-id:3069977572 --> @gabe-l-hart commented on GitHub (Jul 14, 2025): Awesome, much appreciated!
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#29792
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?