-
Notifications
You must be signed in to change notification settings - Fork 379
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
ONNX Model not found #2028
Comments
Hi @trevoradriaanse thanks for reporting this. Just to confirm, you're trying to do the PyPI install, correct? Can you confirm that you're pulling the latest version, 0.43.0? |
Hi @lintool that's correct, I verified that |
Hrm... I can't seem to reproduce this error. Can you try
The server hosting the models has been flaky of late... Perhaps you can try again? |
The Exception is thrown from this location: https://github.com/castorini/anserini/blob/master/src/main/java/io/anserini/search/HnswDenseSearcher.java#L123 But And seems fine...? |
@lintool Thanks for this info. After running |
Are you sure there's not another anserini fatjar that's conflicting? E.g., you did a |
In |
I just tried again from scratch and cannot repro you error... :( What Java version are you on? Mine is: % java --version
openjdk 21.0.5 2024-10-15 LTS
OpenJDK Runtime Environment Zulu21.38+21-CA (build 21.0.5+11-LTS)
OpenJDK 64-Bit Server VM Zulu21.38+21-CA (build 21.0.5+11-LTS, mixed mode, sharing) |
I appreciate the help. I get
|
Hrm. Are you having trouble running all ONNX models? Go here: https://castorini.github.io/pyserini/2cr/msmarco-v1-passage.html Pick another ONNX model and see if it's a BGE-specific issue... |
Yeah, it seems to be a more general problem. I ran
which encounters the same issue:
|
Interesting. Can you try with Anserini? https://github.com/castorini/anserini?tab=readme-ov-file#-try-it Run the two commands and let me know what you see? |
I'm seeing this traceback fragment for
|
I'm perplexed... when I run those two commands, everything works fine. See below for my complete execution trace. Can you pinpoint where you're diverging?
|
I'm seeing
Comparing the two traces, it looks like I also get through the calls to |
Hello!
I'm running the installation instructions for HNSW
and I'm getting the following traceback:
I located the encoder model in my Hugging Face cache and noticed there was a
safetensors
formatted model, but I don't see the ONNX model format. Could this be the issue?The text was updated successfully, but these errors were encountered: