Spaces:
Running
Running
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,12 +1,53 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version:
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: n8n Workflow Generator
|
| 3 |
+
emoji: π
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: purple
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 4.44.1
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
models:
|
| 12 |
+
- Nishan30/n8n-workflow-generator-qwen1.5b
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# π n8n Workflow Generator
|
| 16 |
+
|
| 17 |
+
Generate n8n workflows using natural language! This app uses a fine-tuned **Qwen2.5-Coder-1.5B** model to automatically create n8n automation workflows from simple text descriptions.
|
| 18 |
+
|
| 19 |
+
## π― Model Performance
|
| 20 |
+
|
| 21 |
+
- **Overall Score:** 91.2% (657/720 points)
|
| 22 |
+
- **Grade:** A - Production Ready! β
|
| 23 |
+
- **Training Data:** 2,736 curated workflow examples
|
| 24 |
+
- **Test Cases:** 24 comprehensive tests across 7 patterns
|
| 25 |
+
|
| 26 |
+
## π How to Use
|
| 27 |
+
|
| 28 |
+
1. **Describe your workflow** in plain English
|
| 29 |
+
2. **Click "Generate Workflow"**
|
| 30 |
+
3. **Copy the generated code** or n8n JSON
|
| 31 |
+
4. **Import into your n8n instance**
|
| 32 |
+
|
| 33 |
+
## π Example Prompts
|
| 34 |
+
|
| 35 |
+
- *Create a webhook that sends data to Slack*
|
| 36 |
+
- *Schedule that runs daily and backs up database to Google Drive*
|
| 37 |
+
- *Webhook receives form data, validates email, saves to Airtable*
|
| 38 |
+
- *Monitor RSS feed and post new items to Twitter*
|
| 39 |
+
|
| 40 |
+
## π§ Technical Details
|
| 41 |
+
|
| 42 |
+
- **Base Model:** Qwen/Qwen2.5-Coder-1.5B-Instruct
|
| 43 |
+
- **Fine-tuning:** LoRA (Low-Rank Adaptation)
|
| 44 |
+
- **Training:** 2,462 train + 274 validation examples
|
| 45 |
+
- **Framework:** Transformers + PEFT
|
| 46 |
+
|
| 47 |
+
## π€ Model Card
|
| 48 |
+
|
| 49 |
+
[View full model card and details](https://huggingface.co/Nishan30/n8n-workflow-generator-qwen1.5b)
|
| 50 |
+
|
| 51 |
+
## π License
|
| 52 |
+
|
| 53 |
+
Apache 2.0
|