-
### System Info
Could you please advise me on how to resolve this issue after importing the Transformer library from Hugging Face?
ValueError: TimeSeriesTransformerForPrediction does not support Fla…
-
Hello @shaopengw and team,
Congratulations on this amazing work—the model model looks incredible! 🎉
You should consider adding the model (inference at least) to the Hugging Face Hub 🤗. Doing so co…
-
The results obtained through an LLM using the same prompt are not always the same. Even defining a value of 0 in the temperature. How did you handle this situation to make comparisons of results in yo…
-
Hi, I'm using `BitsAndBytesConfig` on HF's Transformers library to quantize `facebook/opt-66B` model. But when I print the dtype of weights of varoius layers, all of them turn out to be of `int8`.
…
-
## 🚀 Model / language coverage
The idea is to support LLaVa model from HF. This issue is mainly for tracking the status.
Blocking issues:
- [ ] #735
- [ ] #124
### Minimal Repro
First o…
-
Vulnerable Library - transformers-4.26.1-py3-none-any.whl
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
Library home page: https://files.pythonhosted.org/packages/1e/e2/60c3f4691…
-
Im running the colab notebook on free tier GPU and getting errors.
```
/usr/local/lib/python3.10/dist-packages/xformers/ops/fmha/flash.py:211: FutureWarning: `torch.library.impl_abstract` was ren…
-
Is this going to be on the transformers library? Seems like it's going to be big.
-
### System Info
Environment:
OS: Ubuntu 24.04
Python version: 3.11.8
Transformers version: transformers==4.45.2
Torch version: torch==2.3.0
Model: Meta-Llama-3.1-70B-Q2_K-GGUF - https://hugg…
-
**Is your feature request related to a problem? Please describe.**
yes the library needs sharp support
**Describe the solution you'd like**
possibility of using
```javascript
import { pipeline …