RainbowLord/Rainbow-AI-1

Rainbow-AI-Specialist 🌈🤖

Rainbow-AI-Specialist is a custom multi-domain fine-tuned AI model based on google/gemma-2-2b-it, trained using QLoRA via Hugging Face TRL (SFTTrainer).

Domains Covered 🧠

• Python Coding: Clean scripts and algorithmic logic.
• Trading Strategies: Market analysis and financial breakdowns.
• Poetry: Creative and rhythmic writing.
• Nova Persona: Unique character interactions and dialogue.

How to Use 💻

You can load and test this adapter easily in Python using PEFT and Transformers:

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

# Load base model and tokenizer
model_id = "google/gemma-2-2b-it"
tokenizer = AutoTokenizer.from_pretrained(model_id)
base_model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

# Attach your custom Rainbow adapter!
model = PeftModel.from_pretrained(base_model, "RainbowLord/Rainbow-AI-Specialist")

# Test generation
inputs = tokenizer("### User: Write a Python script for a simple trading bot.\n### Rainbow:", return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=150)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))