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 #756] Mistral - Failed To Load Model #62395

New Issue
Closed
opened 2026-05-03 08:46:57 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 08:46:57 -05:00
Owner
Copy Link

Originally created by @mattdavenport on GitHub (Oct 11, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/756

I'm running macOS (Ventura 13.0.1) 16in. M1 2021. I am able to run all of the llama2 models just fine, but the following occurs when attempting to run the mistral model:

~ % ollama pull mistral:latest                                                                                                                                                                                                                                                                                                                                                                                                   
pulling manifest
pulling 6ae280299950... 100% |███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (4.1/4.1 GB, 48 MB/s)
pulling fede2d8d6c1f... 100% |████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (29/29 B, 194 kB/s)
pulling b96850d2e482... 100% |█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████���████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (307/307 B, 1.4 MB/s)
verifying sha256 digest
writing manifest
success
~ % ollama run mistral:latest                                                                                                                                                                                                                                                                                                                                                                                                   
>>> Hello
Error: failed to load model

If this is still a WIP please close this issue. The only other information I could find is the following log entries:

2023/10/11 10:25:47 images.go:1093: redirected to: https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/6a/6ae28029995007a3ee8d0b8556d50f3b59b831074cf19c84de87acf51fb54054/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20231011%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20231011T142546Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=386696851dae4763d830fc88c05381be653dab1e21243686e3180c01011644b6
2023/10/11 10:27:13 images.go:1061: success getting sha256:6ae28029995007a3ee8d0b8556d50f3b59b831074cf19c84de87acf51fb54054
2023/10/11 10:27:14 images.go:1093: redirected to: https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/fe/fede2d8d6c1f404b1db73b1cd26f7d5455ff2deeb737b5e2b339339dce2969d4/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20231011%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20231011T142714Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=4b1d208c4dcb6b20ae9727869c284c8ec0f77ee382ee975d96f50f1c358047e7
2023/10/11 10:27:14 images.go:1061: success getting sha256:fede2d8d6c1f404b1db73b1cd26f7d5455ff2deeb737b5e2b339339dce2969d4
2023/10/11 10:27:15 images.go:1093: redirected to: https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/b9/b96850d2e482b0d1af356eda4ac158af93e9b00e71363a9173d7b5480680bcf3/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20231011%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20231011T142715Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=a5cb6b9a865ca7264746ec67325b71ad80987c800bbeeadd43eef75a6e0363bc
2023/10/11 10:27:15 images.go:1061: success getting sha256:b96850d2e482b0d1af356eda4ac158af93e9b00e71363a9173d7b5480680bcf3
[GIN] 2023/10/11 - 10:27:18 | 200 |         1m33s |       127.0.0.1 | POST     "/api/pull"
llama.cpp: loading model from /Users/mattdavenport/.ollama/models/blobs/sha256:6ae28029995007a3ee8d0b8556d50f3b59b831074cf19c84de87acf51fb54054
error loading model: unknown (magic, version) combination: 46554747, 00000002; is this really a GGML file?
llama_load_model_from_file: failed to load model
[GIN] 2023/10/11 - 11:04:20 | 500 |    3.950083ms |       127.0.0.1 | POST     "/api/generate"

Please let me know if I can provide any additional information here to help debug. Thanks!

Originally created by @mattdavenport on GitHub (Oct 11, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/756 I'm running macOS (Ventura 13.0.1) 16in. M1 2021. I am able to run all of the llama2 models just fine, but the following occurs when attempting to run the mistral model: ``` ~ % ollama pull mistral:latest pulling manifest pulling 6ae280299950... 100% |███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (4.1/4.1 GB, 48 MB/s) pulling fede2d8d6c1f... 100% |████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (29/29 B, 194 kB/s) pulling b96850d2e482... 100% |█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████���████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (307/307 B, 1.4 MB/s) verifying sha256 digest writing manifest success ~ % ollama run mistral:latest >>> Hello Error: failed to load model ``` If this is still a WIP please close this issue. The only other information I could find is the following log entries: ``` 2023/10/11 10:25:47 images.go:1093: redirected to: https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/6a/6ae28029995007a3ee8d0b8556d50f3b59b831074cf19c84de87acf51fb54054/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20231011%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20231011T142546Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=386696851dae4763d830fc88c05381be653dab1e21243686e3180c01011644b6 2023/10/11 10:27:13 images.go:1061: success getting sha256:6ae28029995007a3ee8d0b8556d50f3b59b831074cf19c84de87acf51fb54054 2023/10/11 10:27:14 images.go:1093: redirected to: https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/fe/fede2d8d6c1f404b1db73b1cd26f7d5455ff2deeb737b5e2b339339dce2969d4/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20231011%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20231011T142714Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=4b1d208c4dcb6b20ae9727869c284c8ec0f77ee382ee975d96f50f1c358047e7 2023/10/11 10:27:14 images.go:1061: success getting sha256:fede2d8d6c1f404b1db73b1cd26f7d5455ff2deeb737b5e2b339339dce2969d4 2023/10/11 10:27:15 images.go:1093: redirected to: https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/b9/b96850d2e482b0d1af356eda4ac158af93e9b00e71363a9173d7b5480680bcf3/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20231011%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20231011T142715Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=a5cb6b9a865ca7264746ec67325b71ad80987c800bbeeadd43eef75a6e0363bc 2023/10/11 10:27:15 images.go:1061: success getting sha256:b96850d2e482b0d1af356eda4ac158af93e9b00e71363a9173d7b5480680bcf3 [GIN] 2023/10/11 - 10:27:18 | 200 | 1m33s | 127.0.0.1 | POST "/api/pull" llama.cpp: loading model from /Users/mattdavenport/.ollama/models/blobs/sha256:6ae28029995007a3ee8d0b8556d50f3b59b831074cf19c84de87acf51fb54054 error loading model: unknown (magic, version) combination: 46554747, 00000002; is this really a GGML file? llama_load_model_from_file: failed to load model [GIN] 2023/10/11 - 11:04:20 | 500 | 3.950083ms | 127.0.0.1 | POST "/api/generate" ``` Please let me know if I can provide any additional information here to help debug. Thanks!
GiteaMirror commented 2026-05-03 08:47:00 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Oct 11, 2023):

Hi @mattdavenport, may I ask which version of Ollama you are running? mistral requires 0.19 or above – sorry that's not more obvious! You can get the latest version here

I'll close this for now, but keep the feedback coming (or re-open if you're still seeing this after updating)

<!-- gh-comment-id:1757914412 --> @jmorganca commented on GitHub (Oct 11, 2023): Hi @mattdavenport, may I ask which version of Ollama you are running? `mistral` requires 0.19 or above – sorry that's not more obvious! You can get the latest version [here](https://ollama.ai/download) I'll close this for now, but keep the feedback coming (or re-open if you're still seeing this after updating)
GiteaMirror commented 2026-05-03 08:47:01 -05:00
Author
Owner
Copy Link

@mattdavenport commented on GitHub (Oct 11, 2023):

🤦 That was it. Thanks for the tip, and I appreciate all the great work you've done here!

<!-- gh-comment-id:1757983722 --> @mattdavenport commented on GitHub (Oct 11, 2023): 🤦 That was it. Thanks for the tip, and I appreciate all the great work you've done here!
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#62395
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?