-
### Feature request
`bias` of linear layers in `qwen2` model is hard coded as following:
- https://github.com/huggingface/transformers/blob/85345bb439652d3f03bb4e123cef7a440f2ba95b/src/transformers/…
-
![image](https://github.com/user-attachments/assets/e702965d-a8b2-4d46-a5df-14fc9bae5fa9)
`
2024-09-15 09:16:58,320 - root - INFO - got prompt
2024-09-15 09:17:10,467 - root - ERROR - !!! Exc…
-
With the new release of version 3.2.0, the use of ONNX has become much easier but initial local tests led to various errors, meaning that it was not possible to use ONNX Runtime via Sentence Transform…
-
### System Info
- `transformers` version: 4.45.0.dev0
- Platform: Linux-5.15.0-117-generic-x86_64-with-glibc2.35
- Python version: 3.10.15
- Huggingface_hub version: 0.26.0
- Safetensors versio…
-
As `pytorch-pretrained-bert` is now `huggingface/transformers` do we plan to migrate to `transformers`?
-
It will likely require converting them to HF format/Pytorch, similar to how it's done for the OPUS-MT and HPLT models:
https://huggingface.co/Helsinki-NLP/opus-mt-zh-en
https://huggingface.co/HPLT…
-
### Proposal
Change some code that could load model locally.
### Motivation
Today I want to load gpt2 model that download from huggingface website locally like Llama, but it keeps try to connc…
-
Hello, I tried to train Llama3.2 3B. It's a full finetune, not a lora, but Unsloth always crashes under varying conditions when the model should be saved. Hardware was runpod in all cases, different c…
-
Huggingface transformers has been upgraded from pytorch-pretrained-BERT and BERT_model.py doesn't run
-
Hello, thank you for sharing your excellent project.
When I evaluated it on the multiple-choice QA benchmark **EgoSchema**, I found that the prompt was long than other bench (I guess this may caus…