github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10334] Support microsoft/bitnet-b1.58-2B-4T #53300

New Issue
Closed
opened 2026-04-29 02:33:37 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-29 02:33:37 -05:00
Owner
Copy Link

Originally created by @liudonghua123 on GitHub (Apr 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10334

Hi, I downloaded the gguf of microsoft/bitnet-b1.58-2B-4T via huggingface-cli download microsoft/bitnet-b1.58-2B-4T-gguf --local-dir bitnet-b1.58-2B-4T and created a Makefile which contains FROM ./ggml-model-i2_s.gguf.

Then I tried to execute ollama create bitnet -f Makefile, but it failed with the following errors.

> cd bitnet-b1.58-2B-4T\

> ollama create bitnet -f Makefile
gathering model components
copying file sha256:13939ce5030319a35db346e5dba7a3a3bd599dfc18b113a2a97446ff964714c5 100%
parsing GGUF
Error: invalid file magic

>
Originally created by @liudonghua123 on GitHub (Apr 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10334 Hi, I downloaded the gguf of [microsoft/bitnet-b1.58-2B-4T](https://hf-mirror.com/microsoft/bitnet-b1.58-2B-4T-gguf) via `huggingface-cli download microsoft/bitnet-b1.58-2B-4T-gguf --local-dir bitnet-b1.58-2B-4T` and created a Makefile which contains `FROM ./ggml-model-i2_s.gguf`. Then I tried to execute `ollama create bitnet -f Makefile`, but it failed with the following errors. ```shell > cd bitnet-b1.58-2B-4T\ > ollama create bitnet -f Makefile gathering model components copying file sha256:13939ce5030319a35db346e5dba7a3a3bd599dfc18b113a2a97446ff964714c5 100% parsing GGUF Error: invalid file magic > ```
GiteaMirror added the model label 2026-04-29 02:33:37 -05:00
GiteaMirror commented 2026-04-29 02:34:02 -05:00
Author
Owner
Copy Link

@liudonghua123 commented on GitHub (Apr 18, 2025):

I find some similar issues, https://github.com/ollama/ollama/issues/2821, https://github.com/ollama/ollama/issues/10313, https://github.com/ollama/ollama/issues/7289.

<!-- gh-comment-id:2814407180 --> @liudonghua123 commented on GitHub (Apr 18, 2025): I find some similar issues, https://github.com/ollama/ollama/issues/2821, https://github.com/ollama/ollama/issues/10313, https://github.com/ollama/ollama/issues/7289.
GiteaMirror commented 2026-04-29 02:34:07 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 18, 2025):

https://github.com/ggml-org/llama.cpp/issues/12997

The GGUF file uses a GGML quantization type of 36 which is not supported in llama.cpp or ollama. As a result the block size for those tensors is 0, which causes a misalignment in the tensor read culminating in an invalid file magic error because the read doesn't reach the end of the file.

$ dumpgguf ggml-model-i2_s.gguf
INFO:gguf-dump:* Loading: ggml-model-i2_s.gguf
Traceback (most recent call last):
  File "/app/gguf-py/gguf/scripts/gguf_dump.py", line 454, in <module>
    main()
  File "/app/gguf-py/gguf/scripts/gguf_dump.py", line 439, in main
    reader = GGUFReader(args.model, 'r')
  File "/app/gguf-py/gguf/gguf_reader.py", line 182, in __init__
    self._build_tensors(offs, tensors_fields)
  File "/app/gguf-py/gguf/gguf_reader.py", line 325, in _build_tensors
    ggml_type = GGMLQuantizationType(raw_dtype[0])
  File "/usr/lib/python3.10/enum.py", line 385, in __call__
    return cls.__new__(cls, value)
  File "/usr/lib/python3.10/enum.py", line 710, in __new__
    raise ve_exc
ValueError: 36 is not a valid GGMLQuantizationType
<!-- gh-comment-id:2815404819 --> @rick-github commented on GitHub (Apr 18, 2025): https://github.com/ggml-org/llama.cpp/issues/12997 The GGUF file uses a GGML quantization type of 36 which is not supported in llama.cpp or ollama. As a result the block size for those tensors is 0, which causes a misalignment in the tensor read culminating in an `invalid file magic` error because the read doesn't reach the end of the file. ``` $ dumpgguf ggml-model-i2_s.gguf INFO:gguf-dump:* Loading: ggml-model-i2_s.gguf Traceback (most recent call last): File "/app/gguf-py/gguf/scripts/gguf_dump.py", line 454, in <module> main() File "/app/gguf-py/gguf/scripts/gguf_dump.py", line 439, in main reader = GGUFReader(args.model, 'r') File "/app/gguf-py/gguf/gguf_reader.py", line 182, in __init__ self._build_tensors(offs, tensors_fields) File "/app/gguf-py/gguf/gguf_reader.py", line 325, in _build_tensors ggml_type = GGMLQuantizationType(raw_dtype[0]) File "/usr/lib/python3.10/enum.py", line 385, in __call__ return cls.__new__(cls, value) File "/usr/lib/python3.10/enum.py", line 710, in __new__ raise ve_exc ValueError: 36 is not a valid GGMLQuantizationType ```
GiteaMirror commented 2026-04-29 02:34:09 -05:00
Author
Owner
Copy Link

@qdrddr commented on GitHub (Apr 18, 2025):

This is because it's intended to be run with bitnet.cpp
https://github.com/microsoft/BitNet

<!-- gh-comment-id:2815479230 --> @qdrddr commented on GitHub (Apr 18, 2025): This is because it's intended to be run with bitnet.cpp https://github.com/microsoft/BitNet
GiteaMirror commented 2026-04-29 02:34:10 -05:00
Author
Owner
Copy Link

@electriquo commented on GitHub (Apr 18, 2025):

relates to https://github.com/ollama/ollama/issues/10337

<!-- gh-comment-id:2815876584 --> @electriquo commented on GitHub (Apr 18, 2025): relates to https://github.com/ollama/ollama/issues/10337
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#53300
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?