huggingface / huggingface/diffusers
resize_token_embeddings (?) (different result from new and old version)
- Lingua principale
- Python
- Stelle
- 34.5k
- Fork
- 7.3k
- Merge medio
- 3g 3h
- PR unite (30g)
- 91
Descrizione
### System Info
model, and embending https://huggingface.co/fofr/sdxl-emoji
detail image: [emoji_20250813_002621_2c661c36-1825-496f-84b4-60ec59a961fe.json](https://github.com/user-attachments/files/21756027/emoji_20250813_002621_2c661c36-1825-496f-84b4-60ec59a961fe.json)
from [requirements.txt](https://github.com/user-attachments/files/21755757/requirements.txt)
to:
[new_requirements.txt](https://github.com/user-attachments/files/21755772/new_requirements.txt)
the code is: (not changed)
[generation.txt](https://github.com/user-attachments/files/21755848/generation.txt)
### Who can help?
tokenizers: @ArthurZucker and @itazap
pipelines: @Rocketknight1
### Information
- [ ] The official example scripts
- [x] My own modified scripts
### Tasks
- [ ] An officially supported task in the `examples` folder (such as GLUE/SQuAD, ...)
- [ ] My own task or dataset (give details below)
### Reproduction
code top
### Expected behavior
view image
Guida per i contributori
Apri la guida per i contributori
Direzione di ricerca
Start with the attached generation.txt and compare requirements.txt with new_requirements.txt, then inspect the referenced model and embedding configuration. Reproduce the output difference between the old and new environments and determine whether resize_token_embeddings is involved. Done should include a reproducible explanation or confirmed fix for the changed result, with updated comparison evidence.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Valutazione
- Stack tecnologico
- python, pytorch
- Ambito
- machine-learning
- Tipo di issue
- Bug
- Difficoltà
- 4/5
- Tempo stimato
- 3-5 giorni
- Stato di attività
- Ferma
- Chiarezza
- Da chiarire
- Idoneità per principianti
- 25/100