-
I saw you used something like this:
```
model = FastVisionModel.get_peft_model(
model,
finetune_vision_layers = True, # False if not finetuning vision part
finetune_language_lay…
-
Description: When running inference on the distilbert-base-uncased model using the NPU on Snapdragon® X Elite (X1E78100 - Qualcomm®) through ONNX Runtime's QNNExecutionProvider, the model fails to inf…
-
Hi OpenSora-Plan Team,
Thank you for your excellent work!
I noticed that a new attention pattern was used when training model v1.3, as described below:
> Considering both computational load a…
-
Is there a strict requirement for GPUs that support flash_attention? I tried to test on V100, but this GPU does not support flash_attention, resulting in an error with the Runtime Error: No available …
-
When I run `./eval.sh`, it rise the error as below
```shell
export PYTHONPATH=$(pwd)
export HF_ENDPOINT=https://hf-mirror.com
export HF_TOKEN=hf_xxx
model_path="/data/tbsi/train_log/llavanext/2…
-
### The model to consider.
https://huggingface.co/dunzhang/stella_en_1.5B_v5
last_hidden_state = model(**input_data)[0]
in __init__ model:
vector_linear = torch.nn.Linear(in_features=model.conf…
-
Dear Sir/Miss,
how to use the "raw" draw the heatmap?
-
### System Info
- `transformers` version: 4.46.2
- Platform: Linux-6.1.85+-x86_64-with-glibc2.35
- Python version: 3.10.12
- Huggingface_hub version: 0.24.7
- Safetensors version: 0.4.5
- Accele…
-
I found these greatly improved SDXL speed, like 25% on my 3060. can you make a node for unet models, because most flux models are unet. I would like to try it on flux
-
### 🐛 Describe the bug
As mentioned in this [blog](https://dev-discuss.pytorch.org/t/higher-order-operators-2023-10/1565), HigherOrderOperator does not support graph break inside the input/output fun…