Pattern	Score	Tests
webhook_simple	93.3%	3
data_processing	96.7%	1
webhook_conditional	90.0%	2
schedule_simple	90.0%	1
schedule_complex	93.3%	1
form	93.3%	1
integration	93.3%	1
error_handling	93.3%	1

Results by Difficulty

Difficulty	Average Score	Tests
Easy	92.5%	4
Medium	91.8%	11
Hard	89.5%	7
Very Hard	91.7%	2

🚀 Quick Start

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-Coder-1.5B-Instruct",
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "Nishan30/n8n-workflow-generator-qwen1.5b")
model.eval()

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(
    "Qwen/Qwen2.5-Coder-1.5B-Instruct",
    trust_remote_code=True
)

# Generate workflow
SYSTEM_PROMPT = """You are an expert n8n workflow generator. n8n is a powerful workflow automation tool that connects various services and APIs.

Your task is to generate TypeScript DSL code for n8n workflows based on user requests.

Generate ONLY the TypeScript DSL code, wrapped in ```typescript code blocks."""

user_prompt = "Create a webhook that sends data to Slack"

formatted_prompt = f"""### System:
{SYSTEM_PROMPT}

### Instruction:
{user_prompt}

### Response:
"""

inputs = tokenizer(formatted_prompt, return_tensors="pt", truncation=True, max_length=2048).to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.3,
        top_p=0.95,
        top_k=50,
        repetition_penalty=1.1,
        do_sample=True
    )

result = tokenizer.decode(outputs[0], skip_special_tokens=True)
response = result.split("### Response:")[-1].strip()
print(response)

💡 Example Outputs

Simple Webhook → Slack

typescript

const workflow = new Workflow('Slack Webhook');
const createWebhook = workflow.add('n8n-nodes-base.webhook', {"path": "/slack", "method": "POST"});
const sendToSlack = workflow.add('n8n-nodes-base.slack', {"channel": "#general", "text": "={{ $json.message }}"});

createWebhook.to(sendToSlack);

Data Pipeline

typescript

const workflow = new Workflow('Data Pipeline');
const trigger = workflow.add('n8n-nodes-base.webhook', {"path": "/api/data-pipeline"});
const transform = workflow.add('n8n-nodes-base.set', {"values": [{"name": "id", "value": "={{ $json.id }"}}]});
const filter = workflow.add('n8n-nodes-base.filter', {"conditions": [{"leftValue": "={{ $json.status }}", "operation": "===", "rightValue": "active"}]});

trigger.to(transform);
transform.to(filter);

📝 Model Details

Base Model: Qwen/Qwen2.5-Coder-1.5B-Instruct
Fine-tuning Method: LoRA (Low-Rank Adaptation)
Parameters: 1.5B base + LoRA adapters
Training Framework: Transformers + PEFT
Hardware: NVIDIA Tesla T4 GPU

🎓 Training Configuration

LoRA Rank: 16
LoRA Alpha: 32
Learning Rate: 2e-4
Batch Size: 1 (gradient accumulation: 4)
Optimizer: AdamW 8-bit
Epochs: 3
Mixed Precision: FP16

Nishan30/
n8n-workflow-generator-qwen1.5b

n8n Workflow Generator (Qwen 1.5B - LoRA)

🎯 Performance

📊 Detailed Test Results

Results by Pattern

Results by Difficulty

🚀 Quick Start

💡 Example Outputs

Simple Webhook → Slack

Data Pipeline

📝 Model Details

🎓 Training Configuration

📄 License

🙏 Acknowledgments

🔗 Resources