Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Can't infer qwen2.5-7b-instruct with vllm #45

Closed
alekseymalakhov11 opened this issue Oct 21, 2024 · 0 comments · Fixed by #59
Closed

Can't infer qwen2.5-7b-instruct with vllm #45

alekseymalakhov11 opened this issue Oct 21, 2024 · 0 comments · Fixed by #59

Comments

@alekseymalakhov11
Copy link
Collaborator

alekseymalakhov11 commented Oct 21, 2024 •
edited
Loading 

2024-10-21 20:02:35.0004Z [rank0]:     return self._encode(records, inference=True, random_cut=self._random_cut)
2024-10-21 20:02:35.0406Z [rank0]:   File "/app/turbo-alignment/turbo_alignment/dataset/chat/chat.py", line 310, in _encode
input_ids': torch.LongTensor(input_ids),
2024-10-21 20:02:35.1570Z [rank0]: TypeError: can't convert np.ndarray of type numpy.object_. The only supported types are: float64, float32, float16, complex64, complex128, int64, int32, int16, int8, uint64, uint32, uint16, uint8, and bool.
@alekseymalakhov11 alekseymalakhov11 linked a pull request Nov 20, 2024 that will close this issue
📎 Fix tokenization dtypes #59
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

📎 Fix tokenization dtypes turbo-llm/turbo-alignment
1 participant
@alekseymalakhov11