Reasoningcore 3B R01

🚀 ReasoningCore‑3B-RE01

ReasoningCore‑3B is a multilingual, reasoning‑enhanced large language model developed by EpitemeAI. Pretrained on a vast amount of publicly available data and instruction‑tuned, it excels at nuanced reasoning, dialogue management, retrieval, and summarization tasks. It often outperforms many current open - source and proprietary conversational models on a range of industry benchmarks. It is fine - tuned with a reasoning dataset.

⚠️ Important Note

This is an experimental model.

✨ Features

• Multilingual support for various common languages.
• Enhanced reasoning capabilities through fine - tuning with a reasoning dataset.
• Built - in safety guardrails and can be further enhanced with additional safeguards.

📦 Installation

Ensure you have transformers version 4.43.0 or later installed:

pip install --upgrade transformers

💻 Usage Examples

Basic Usage

Use system prompt

SYSTEM_PROMPT = """
Respond in the following format:
<reasoning>
...
</reasoning>
<answer>
...
</answer>
"""

Use with Transformers

import torch
from transformers import pipeline

model_id = "EpistemeAI/ReasoningCore-3B-R01"
pipe = pipeline(
    "text-generation", 
    model=model_id, 
    torch_dtype=torch.bfloat16, 
    device_map="auto"
)
print(pipe("The secret to effective reasoning is"))

Advanced Usage

For Mathematical problems

Please use "Please reason step by step, and put your final answer within \boxed{}" in the system prompt.

📚 Documentation

Model Information

Intended Use

Use Cases

• Conversational AI: Assistant - like interactions.
• Knowledge Retrieval & Summarization: Dynamic extraction and condensation of information.
• Mobile AI - Powered Writing Assistants: Query reformulation and natural language generation.
• General Natural Language Generation: Any application that benefits from advanced reasoning abilities.

Out of Scope

• Deployments that violate applicable laws or trade compliance regulations.
• Use cases that conflict with the Acceptable Use Policy or licensing terms.
• Deployments in languages not explicitly supported (unless additional safety and performance validations are performed).

Responsibility & Safety

Responsible Deployment

• Approach: ReasoningCore‑3B is a foundational technology that includes built - in safety guardrails. Developers are encouraged to integrate additional safeguards tailored to their specific applications.
• System - Level Safety: The model is designed to be deployed as part of a broader system that implements safety measures (e.g., Prompt Guard, Code Shield) to ensure outputs remain safe even under adversarial conditions.

Safety Fine - Tuning & Data Strategy

• Objectives:
  • Provide a reliable tool for building secure and helpful reasoning systems.
  • Mitigate adversarial misuse through advanced data selection and response optimization techniques.
• Methodology:
  • Incorporate adversarial prompts during training to refine model refusals and response tone.
  • Combine human - curated data with synthetic data.
  • Utilize iterative fine - tuning using supervised learning, rejection sampling, and preference optimization.

Evaluations and Red Teaming

• Scaled Evaluations: Dedicated adversarial datasets were used to rigorously test the model’s robustness. Developers should perform context - specific evaluations.
• Red Teaming: Experts in cybersecurity, adversarial machine learning, and responsible AI conducted recurring red team exercises to identify vulnerabilities and improve both performance and safety.

Critical Risk Mitigations

• CBRNE: The model has been evaluated to ensure it does not enhance capabilities for harmful activities involving chemical, biological, radiological, nuclear, or explosive materials.
• Child Safety: Expert assessments were conducted to evaluate and mitigate potential child safety risks.
• Cyber Attacks: Measures were taken to ensure the model cannot autonomously facilitate cyber - offensive operations.

Ethical Considerations and Limitations

• Core Values: ReasoningCore‑3B is built on the values of openness, inclusivity, and helpfulness. It is designed to respect user autonomy and foster free thought and expression while mitigating potential harm.
• Testing and Limitations: Despite extensive testing across diverse scenarios, the model may occasionally produce inaccurate, biased, or objectionable outputs. Developers must perform additional safety testing and integrate further safeguards as needed.
• Resources for Safe Deployment, with Meta Safety Deployment:
  • [Responsible Use Guide](https://llama.meta.com/responsible - use - guide)
  • [Trust and Safety Resources](https://llama.meta.com/trust - and - safety)
  • [Getting Started Guide](https://llama.meta.com/docs/get - started)

📄 License

The uploaded model is developed by EpistemeAI and is under the apache - 2.0 license. It is finetuned from the model EpistemeAI/ReasoningCore-3B-0. This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.