nyc-vc-match

widget:

• text: "I'm building a B2B SaaS platform for inventory management. We're pre-revenue but have an MVP. Which NYC VCs should I target for seed funding?" example_title: "B2B SaaS Seed Funding"
• text: "Our FinTech startup has $50K MRR and we're raising Series A. Which VCs specialize in FinTech?" example_title: "FinTech Series A"
• text: "We're a healthtech startup using AI for medical imaging. Looking for pre-seed funding. Which VCs should we approach?" example_title: "HealthTech Pre-seed"

---

VC Matching Expert Model

This is a fine-tuned language model specialized in matching startups with appropriate venture capital firms, particularly focused on the NYC ecosystem.

Model Description

• Base Model: microsoft/DialoGPT-small
• Fine-tuning Method: LoRA (Low-Rank Adaptation)
• Specialization: Venture Capital and startup matching
• Geographic Focus: New York City VCs
• Dataset: {dataset_info}

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

# Load model
tokenizer = AutoTokenizer.from_pretrained("{hub_model_name}")
base_model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-small")
model = PeftModel.from_pretrained(base_model, "{hub_model_name}")

# Generate recommendation
prompt = '''### System:
You are a VC matching expert helping startups find the right investors in NYC.

### Human:
I'm building a B2B SaaS platform. Which VCs should I target?

### Assistant:
'''

inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=300, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response.split("### Assistant:")[-1])

Training Details

• Training Framework: HuggingFace Transformers + PEFT
• Training Environment: Google Colab
• Epochs: 3
• Learning Rate: 2e-4
• Batch Size: 1 (with gradient accumulation)

Limitations

• Focused on NYC VC ecosystem
• Training data may not reflect most recent market conditions
• Recommendations should be verified with current market research

Intended Use

This model is designed to help entrepreneurs identify potentially relevant VCs for their startups. It should be used as a starting point for research, not as definitive investment advice. """