Rainbow-AI-12B-Unified

Rainbow-AI-12B-Unified is a custom-trained, multi-domain 12B parameter language model built on an Unsloth-optimized Gemma-4 base architecturespan_3span_3. It features tailored conversational capabilities spanning coding, visual analytics, creative tasks, and a specialized Nova persona mode.

Model Details

  • Base Model: Gemma-2-12B-IT (optimized via Unsloth)span_4span_4
  • Training Type: Supervised Fine-Tuning (SFT) over 60 stepsspan_5span_5
  • Target Domain: Multi-domain assistant with the Nova personaspan_6span_6
  • Format: 16-bit merged safetensorsspan_7span_7

Intended Use

Designed to run as a backend engine for the Rainbow-AI platform, serving diverse user intents from code generation and debugging to structured analytics and kid-friendly creative interactions.

Quickstart Code

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "RainbowLord/Rainbow-AI-12B-Unified"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto"
)
Downloads last month
85
Safetensors
Model size
12B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for RainbowLord/Rainbow-AI-12B-Unified

Quantizations
2 models

Spaces using RainbowLord/Rainbow-AI-12B-Unified 2