-
Dear all,
Thank you so much for sharing the llama3.2 vision model fine-tuning script so fast!
I got the following error when running the demo
```
The model weights are not tied. Please use t…
-
Hii,
I am facing issue with delay in model loading and also the time taken to generate the video from Image.
Currently it is taking 8minutes for 8 seconds video, I have 48GB VRAM , but still it …
-
`# Preparation for inference
messages = [
{
"role": "user",
"content": [
{
"type": "image",
…
-
配置文件:
model:
arch: bita_former
model_type: pretrain_vitL
load_pretrained: False # pretained from scratch
freeze_vit: True
datasets:
rsicd_caption:
vis_processor:
trai…
-
**Description**
I use a model ensemble with 3 models: pre-processor, inference model and post-processor. I want to send one image to the server and generate **n** patches of the given image in the pr…
-
### Feature request
I would like to request the addition of separate projection layers (`q_proj, k_proj, v_proj`) for the attention mechanisms in the `SamModel`. Currently, it uses a combined qkv p…
-
使用Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4,遇到报错RuntimeError: expected mat1 and mat2 to have the same dtype, but got: float != c10::BFloat16
-
### System Info
- `transformers` version: 4.43.3
- Platform: Windows-10-10.0.22631-SP0
- Python version: 3.10.14
- Huggingface_hub version: 0.24.3
- Safetensors version: 0.4.3
- Accelerate versi…
-
### System Info
- `transformers` version: 4.45.0.dev0
- Platform: Linux-5.4.0-167-generic-x86_64-with-glibc2.35
- Python version: 3.10.12
- Huggingface_hub version: 0.25.0
- Safetensors version: …
-
**Describe the bug/ 问题描述 (Mandatory / 必填)**
GPU环境 TrOCR预训练模型微调 求梯度时报错 RuntimeError: The pointer[tensor] is null.
- **Hardware Environment(`Ascend`/`GPU`/`CPU`) / 硬件环境**:
> Modelarts CPU 8核32G…