Update README.md
Browse files
README.md
CHANGED
@@ -1,47 +1,63 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
datasets:
|
4 |
-
-
|
5 |
-
- fka/awesome-chatgpt-prompts
|
6 |
-
- gopipasala/fka-awesome-chatgpt-prompts
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
-
- bertscore
|
10 |
- bleu
|
11 |
-
-
|
12 |
-
-
|
13 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
-
# Model Card for
|
|
|
17 |
|
18 |
-
<!-- Provide a quick summary of what the model is/does. -->
|
19 |
|
20 |
-
|
21 |
-
|
22 |
-
## Model Details
|
23 |
-
|
24 |
-
### Model Description
|
25 |
-
|
26 |
-
<!-- Provide a longer summary of what this model is. -->
|
27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
|
|
29 |
|
30 |
-
|
31 |
-
|
32 |
-
- **Shared by [optional]:** [More Information Needed]
|
33 |
-
- **Model type:** [More Information Needed]
|
34 |
-
- **Language(s) (NLP):** [More Information Needed]
|
35 |
-
- **License:** [More Information Needed]
|
36 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
37 |
|
38 |
-
|
39 |
|
40 |
-
|
|
|
|
|
41 |
|
42 |
-
|
43 |
-
- **Paper [optional]:** [More Information Needed]
|
44 |
-
- **Demo [optional]:** [More Information Needed]
|
45 |
|
46 |
## Uses
|
47 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- zh
|
5 |
+
license: apache-2.0
|
6 |
+
library_name: pytorch
|
7 |
+
tags:
|
8 |
+
- multimodal
|
9 |
+
- vqa
|
10 |
+
- text
|
11 |
+
- audio
|
12 |
datasets:
|
13 |
+
- synthetic-dataset
|
|
|
|
|
14 |
metrics:
|
15 |
- accuracy
|
|
|
16 |
- bleu
|
17 |
+
- wer
|
18 |
+
model-index:
|
19 |
+
- name: AutoModel
|
20 |
+
results:
|
21 |
+
- task:
|
22 |
+
type: vqa
|
23 |
+
name: Visual Question Answering
|
24 |
+
dataset:
|
25 |
+
type: synthetic-dataset
|
26 |
+
name: Synthetic Multimodal Dataset
|
27 |
+
split: test
|
28 |
+
metrics:
|
29 |
+
- type: accuracy
|
30 |
+
value: 85
|
31 |
---
|
32 |
|
33 |
+
# Model Card for AutoModel
|
34 |
+
AutoModel 是一个多模态模型,支持图像、文本和语音输入...
|
35 |
|
|
|
36 |
|
37 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
|
39 |
+
### **3. 提供可下载文件**
|
40 |
+
确保以下文件已上传到仓库,便于用户下载和运行:
|
41 |
+
- **模型权重文件**(如 `AutoModel.pth`)。
|
42 |
+
- **配置文件**(如 `config.json`)。
|
43 |
+
- **依赖文件**(如 `requirements.txt`)。
|
44 |
+
- **运行脚本**(如 `run_model.py`)。
|
45 |
+
widget:
|
46 |
+
- text: "Jens Peter Hansen kommer fra Danmark"
|
47 |
+
用户可以直接下载这些文件并运行模型。
|
48 |
|
49 |
+
---
|
50 |
|
51 |
+
### **4. 自动运行模型的限制**
|
52 |
+
Hugging Face Hub 本身不能自动运行上传的模型,但通过 `Spaces` 提供的接口可以解决这一问题。`Spaces` 能够运行托管的推理服务,让用户无需本地配置即可测试模型。
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
+
---
|
55 |
|
56 |
+
### **推荐方法**
|
57 |
+
- **快速测试**:使用 Hugging Face `Spaces` 创建在线演示。
|
58 |
+
- **高级使用**:在模型卡中提供完整的运行说明,允许用户本地运行模型。
|
59 |
|
60 |
+
通过这些方式,您可以让模型仓库既支持在线运行,也便于用户离线部署。
|
|
|
|
|
61 |
|
62 |
## Uses
|
63 |
|