Gemma 3 4b Reasoning

🚀 Gemma-3-4b Reasoning R1 Model Card

Gemma-3-4b Reasoning is a transformer-based language model fine-tuned with GRPO for reasoning tasks, leveraging the DeepSeek-R1 methodology.

🚀 Quick Start

The model uses structured XML templates for dialogue and reasoning tasks. Here is a basic example to show how to use it:

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "ericrisco/gemma-3-4b-reasoning"

prompt = "A cyclist travels 60 km in 3 hours at a constant speed. If he maintains the same speed, how many kilometers will he travel in 5 hours?"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, device_map="auto", torch_dtype=torch.bfloat16
)

messages = [{"role": "user", "content": prompt}]

input_text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=200)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

print(response)

✨ Features

• Reasoning Focused: Gemma-3-4b Reasoning is a fine - tuned model designed to excel in structured, logical problem - solving and mathematical reasoning.
• Enhanced Reasoning Ability: Trained on the GSM8K dataset using GRPO, it can reason step - by - step and provide structured explanations.
• Robust CoT Capabilities: The model exhibits robust internal Chain - of - Thought (CoT) capabilities, consistently demonstrating detailed explanations and structured problem - solving skills across reasoning tasks.

📦 Installation

The documentation does not provide specific installation steps, so this section is skipped.

📚 Documentation

Model Details

Description

Gemma-3-4b Reasoning is a reasoning - focused fine - tuned model designed to excel in structured, logical problem - solving and mathematical reasoning. The training was performed on the GSM8K dataset using GRPO, enhancing the model's ability to reason step - by - step and provide structured explanations.

Training Dataset

• GSM8K (English): Specialized dataset for mathematical and logical reasoning problems.

Intended Use

Direct Use

The model is specifically designed for structured reasoning tasks, including:

• Mathematical and logical reasoning
• Multi - step problem solving
• Instruction - based reasoning

Out-of-scope Use

This model should not be used for unethical or malicious activities that breach legal and ethical standards.

Performance

The Gemma-3-4b Reasoning model exhibits robust internal Chain - of - Thought (CoT) capabilities, consistently demonstrating detailed explanations and structured problem - solving skills across reasoning tasks.

Limitations

The model is primarily optimized for numeric and structured reasoning and might produce less accurate or unexpected results when applied to unrelated tasks.

Citations

• Gemma Multimodal Reasoning Model by Google
• GRPO Implementation by TRL

Author

Eric Risco

🔧 Technical Details

The documentation does not provide specific technical details, so this section is skipped.

📄 License

The entire Gemma-3-4b Reasoning family is available under a permissive Apache 2.0 license. All training scripts and configurations used are publicly accessible.

📋 Model Information