-
### 📦 部署环境
Docker
### 📌 软件版本
v1.20.2
### 💻 系统环境
Windows
### 🌐 浏览器
Edge
### 🐛 问题描述
![image](https://github.com/user-attachments/assets/77275b11-e81e-412d-8713-a08582319d9a)
会发生回复中断,百分百出现问题,而使…
-
### System Info
- `transformers` version: 4.46.0.dev0
- Platform: macOS-15.0-arm64-arm-64bit
- Python version: 3.11.6
- Huggingface_hub version: 0.25.1
- Safetensors version: 0.4.5
- Accelerate …
-
- [ ] [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://arxiv.org/html/2403.05525v2)
# DeepSeek-VL: Towards Real-World Vision-Language Understanding
**Abstract**
We present De…
-
**Paper**
Character-level Convolutional Networks for Text Classification
**Introduction**
In the realm of text classification, most models have considered the words as the building blocks. This r…
-
### What happened?
Hello everyone,
I have connected the [gemini-pro-vision model via openrouter.ai](https://openrouter.ai/models/google/gemini-pro-vision), but I always get the following error m…
-
- https://arxiv.org/abs/2110.04544
- 2021
大規模な対照的な視覚言語の事前学習により、視覚表現の学習に大きな進歩が見られました。
固定されたラベルのセットで訓練された従来の視覚システムとは異なり、オープンボキャブラリーの設定で画像と生のテキストを合わせることを直接学習するという新しいパラダイムが導入されました。
下流のタスクでは、慎重に選択された…
e4exp updated
2 years ago
-
使用命令:
`
swift eval
--eval_dataset POPE
--ckpt_dir outputs/llava1_5-7b-instruct/v0-20240909-235840/checkpoint-250
--merge_lora true
--eval_output_dir eval_outputs/lora
`
日志信息:
2024-09-…
-
# Papers
- Sapiens: Foundation for Human Vision Models
- 메타에서 나온 Human foundation model ㄷㄷㄷ
- 2D pose estimation, body-part segmentation, depth prediction and normal prediction이 하나의 모델에서 …
-
The Phi3 vision model is excellent and does a great job in extracting text. I am using the CPU version via C# DirectML package.
1. What is the max image filesize in kb that can be sent to the mode…
-
I can do the following to search for papers: `curl 'https://huggingface.co/api/papers/search?q=attention'`
And I get this:
>[{"id":"2409.07146","title":"Gated Slot Attention for Efficient Linear…