chrissoria commited on
Commit
b9d8439
·
verified ·
1 Parent(s): 0f7ceb6

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +39 -7
README.md CHANGED
@@ -1,12 +1,44 @@
1
  ---
2
- title: CatVader
3
- emoji: 💻
4
- colorFrom: pink
5
- colorTo: gray
6
- sdk: gradio
7
- sdk_version: 6.8.0
8
  app_file: app.py
9
  pinned: false
 
 
10
  ---
11
 
12
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ title: CatVader - Social Media Classifier
3
+ emoji: 🐱
4
+ colorFrom: yellow
5
+ colorTo: yellow
6
+ sdk: streamlit
7
+ sdk_version: "1.32.0"
8
  app_file: app.py
9
  pinned: false
10
+ license: mit
11
+ short_description: Classify social media posts using LLMs
12
  ---
13
 
14
+ # CatVader - Social Media Classifier
15
+
16
+ A web interface for the [cat-vader](https://github.com/chrissoria/cat-vader) Python package. Classify social media posts into custom categories using various LLM providers.
17
+
18
+ ## How to Use
19
+
20
+ 1. **Upload Your Data**: Upload a CSV or Excel file containing social media posts
21
+ 2. **Select Column**: Choose the column containing the text to classify
22
+ 3. **Define Categories**: Enter your classification categories (e.g., "Positive", "Negative", "Neutral")
23
+ 4. **Choose a Model**: Select your preferred LLM (free models available!)
24
+ 5. **Click Classify**: View and download results with category assignments
25
+
26
+ ## Supported Models
27
+
28
+ | Provider | Models |
29
+ |----------|--------|
30
+ | **OpenAI** | gpt-4o, gpt-4o-mini |
31
+ | **Anthropic** | Claude Sonnet, Claude Haiku |
32
+ | **Google** | Gemini 2.5 Flash, Gemini 2.5 Pro |
33
+ | **Mistral** | Mistral Large, Mistral Small |
34
+ | **xAI** | Grok models |
35
+ | **HuggingFace** | Qwen, Llama 4, DeepSeek, and thousands more |
36
+
37
+ ## Features
38
+
39
+ - **Multi-label classification**: Assign multiple categories per post
40
+ - **Social media context**: Inject platform, handle, and hashtag context into prompts
41
+ - **Image classification**: Classify posts with images or image URL columns
42
+ - **Multi-model ensemble**: Run multiple models and use majority voting
43
+ - **Batch processing**: Handle thousands of posts efficiently
44
+ - **CSV/Excel export**: Download results ready for analysis