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 #1395] Model filenames (are incompatible with other programs) #62775

New Issue
Closed
opened 2026-05-03 10:17:16 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-03 10:17:16 -05:00
Owner
Copy Link

Originally created by @marco-trovato on GitHub (Dec 6, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1395

I already have a folder with several LLM models, each one can be 20-40 GB.

ollama is unable to load them, i have to pull them again one by one, and they will so they will get saved by ollama according to their HASH, i.e.:

.../ollama_models/blobs/sha256:843d506c69eed7ece9a1584965be88421d9774a82bffd59e992d5a73eac2dee0

Of course I could run (it works):
python3 ./koboldcpp.py --useclblast 0 0 --gpulayers 20 --model /mypath/ollama_models/blobs/sha256:843d506c69eed7ece9a1584965be88421d9774a82bffd59e992d5a73eac2dee0

But am I am supposed to save a second copy of all those 200 GB files just because the filename are expected like this by ollama?

PROPOSED SOLUTION:
Please save the filenames as their model name, i.e.: "wizardcoder_34b-python-q4_K_M.bin" since everyone has a "LLM-models" folder already full of huge files

Originally created by @marco-trovato on GitHub (Dec 6, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1395 I already have a folder with several LLM models, each one can be 20-40 GB. ollama is unable to load them, i have to pull them again one by one, and they will so they will get saved by ollama according to their HASH, i.e.: `.../ollama_models/blobs/sha256:843d506c69eed7ece9a1584965be88421d9774a82bffd59e992d5a73eac2dee0` Of course I could run (it works): `python3 ./koboldcpp.py --useclblast 0 0 --gpulayers 20 --model /mypath/ollama_models/blobs/sha256:843d506c69eed7ece9a1584965be88421d9774a82bffd59e992d5a73eac2dee0` But am I am supposed to save a second copy of all those 200 GB files just because the filename are expected like this by ollama? PROPOSED SOLUTION: **Please save the filenames as their model name, i.e.: "wizardcoder_34b-python-q4_K_M.bin"** since everyone has a "LLM-models" folder already full of huge files
GiteaMirror commented 2026-05-03 10:17:18 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Dec 6, 2023):

Thanks for submitting this! This is related to the model export and import feature request on #335. Closing this so we don't have duplicates, and definitely happy to continue the conversation there.

<!-- gh-comment-id:1841918019 --> @mchiang0610 commented on GitHub (Dec 6, 2023): Thanks for submitting this! This is related to the model export and import feature request on #335. Closing this so we don't have duplicates, and definitely happy to continue the conversation there.
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#62775
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?