ibm / granite-3_3-8b-instruct

Granite-3.3-8B-Instruct Overview

Description

Granite-3.3-8B-Instruct is an 8-billion parameter language model with a 128K context length, fine-tuned for enhanced reasoning and instruction-following capabilities. Built upon Granite-3.3-8B-Base, it demonstrates significant improvements on benchmarks such as AlpacaEval-2.0 and Arena-Hard, as well as in tasks involving mathematics, coding, and instruction adherence. The model supports structured reasoning through the use of <think> and <response> tags, enabling a clear separation between internal thoughts and final outputs. It has been trained on a carefully balanced combination of permissively licensed data and curated synthetic tasks.

This model is ready for commercial and non-commercial use.

Third-Party Community Consideration

This model is not owned or developed by NVIDIA. It has been developed and built to IBM's requirements for this application and use case; see the Granite-3.3-8B-Instruct Model Card

License and Terms of Use

GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the NVIDIA Community Model License. Additional Information: Apache 2.0.

Deployment Geography

Global

Use Case

Designed to handle general instruction-following tasks, Granite-3.3-8B-Instruct can be integrated into AI assistants across various domains, including business applications.

Supported Languages:
English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. However, users may finetune this Granite model for languages beyond these 12 languages.

Capabilities

  • Thinking
  • Summarization
  • Text classification
  • Text extraction
  • Question-answering
  • Retrieval Augmented Generation (RAG)
  • Code related tasks
  • Function-calling tasks
  • Multilingual dialog use cases
    • Fill-in-the-middle
  • Long-context tasks including long document/meeting summarization, long document QA, etc.

Release Date

  • Hugging Face: April 16, 2025
  • Build.nvidia.com: May, 2025

References

Model Architecture

  • Architecture Type: Transformer (Decoder-only)
  • Network Architecture: Granite
  • Base Model: Granite-3.3-8B-Base
  • Model Parameters: 8 billion

Input

  • Input Type: Text
  • Input Format: String
  • Input Parameters: One-Dimensional (1D)
  • Other Properties Related to Input: Supports up to 128K tokens context length.

Output

  • Output Type: Text
  • Output Format: String
  • Output Parameters: One-Dimensional (1D)
  • Other Properties Related to Output: Capable of generating structured responses using <think> and <response> tags.

Preferred/Supported Operating System(s)

  • Linux
  • Windows

Model Version(s)

  • Granite-3.3-8B-Instruct v1.0

Training, Testing, and Evaluation Datasets

Training Dataset

  • Link: Undisclosed
  • Data Collection Method: Undisclosed
  • Labeling Method: Undisclosed
  • Properties: Undisclosed

Testing Dataset

  • Link: Undisclosed
  • Data Collection Method: Undisclosed
  • Labeling Method: Undisclosed
  • Properties: Undisclosed

Evaluation Dataset

  • Benchmark Score: Undisclosed
  • Data Collection Method: Undisclosed
  • Labeling Method: Undisclosed
  • Properties: Undisclosed

Evaluation Results:

Comparison with different models over various benchmarks1. Scores of AlpacaEval-2.0 and Arena-Hard are calculated with thinking=True
Models Arena-Hard AlpacaEval-2.0 MMLU PopQA TruthfulQA BigBenchHard2 DROP3 GSM8K HumanEval HumanEval+ IFEval AttaQ
Granite-3.1-2B-Instruct 23.3 27.17 57.11 20.55 59.79 61.82 20.99 67.55 79.45 75.26 63.59 84.7
Granite-3.2-2B-Instruct 24.86 34.51 57.18 20.56 59.8 61.39 23.84 67.02 80.13 73.39 61.55 83.23
Granite-3.3-2B-Instruct 28.86 43.45 55.88 18.4 58.97 63.91 44.33 72.48 80.51 75.68 65.8 87.47
Llama-3.1-8B-Instruct 36.43 27.22 69.15 28.79 52.79 73.43 71.23 83.24 85.32 80.15 79.10 83.43
DeepSeek-R1-Distill-Llama-8B 17.17 21.85 45.80 13.25 47.43 67.39 49.73 72.18 67.54 62.91 66.50 42.87
Qwen-2.5-7B-Instruct 25.44 30.34 74.30 18.12 63.06 69.19 64.06 84.46 93.35 89.91 74.90 81.90
DeepSeek-R1-Distill-Qwen-7B 10.36 15.35 50.72 9.94 47.14 67.38 51.78 78.47 79.89 78.43 59.10 42.45
Granite-3.1-8B-Instruct 37.58 30.34 66.77 28.7 65.84 69.87 58.57 79.15 89.63 85.79 73.20 85.73
Granite-3.2-8B-Instruct 55.25 61.19 66.79 28.04 66.92 71.86 58.29 81.65 89.35 85.72 74.31 84.7
Granite-3.3-8B-Instruct 57.56 62.68 65.54 26.17 66.86 69.13 59.36 80.89 89.73 86.09 74.82 88.5
Math Benchmarks
Models AIME24 MATH-500
Granite-3.1-2B-Instruct 0.89 35.07
Granite-3.2-2B-Instruct 0.89 35.54
Granite-3.3-2B-Instruct 3.28 58.09
Granite-3.1-8B-Instruct 1.97 48.73
Granite-3.2-8B-Instruct 2.43 52.8
Granite-3.3-8B-Instruct 8.12 69.02

Inference

  • Engine: vLLM
  • Test Hardware: NVIDIA Ada Lovelace

Additional Details

Generation:
This is a simple example of how to use Granite-3.3-8B-Instruct model.

Install the following libraries:

pip install torch torchvision torchaudio
pip install accelerate
pip install transformers

Then, copy the snippet from the section that is relevant for your use case.

from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
import torch

model_path="ibm-granite/granite-3.3-8b-instruct"
device="cuda"
model = AutoModelForCausalLM.from_pretrained(
        model_path,
        device_map=device,
        torch_dtype=torch.bfloat16,
    )
tokenizer = AutoTokenizer.from_pretrained(
        model_path
)

conv = [{"role": "user", "content":"Redesign a common household item to make it more sustainable and user-friendly. Explain the changes and their benefits."}]

input_ids = tokenizer.apply_chat_template(conv, return_tensors="pt", thinking=True, return_dict=True, add_generation_prompt=True).to(device)

set_seed(42)
output = model.generate(
    **input_ids,
    max_new_tokens=8192,
)

prediction = tokenizer.decode(output[0, input_ids["input_ids"].shape[1]:], skip_special_tokens=True)
print(prediction)

Example Outputs

  • thinking=True
<think>To address this prompt, I'll focus on redesigning a common household item: the plastic water bottle. The goal is to make it more sustainable and user-friendly. Here are the proposed changes and their benefits:

1. **Material**: Replace plastic with biodegradable or recyclable materials like glass or plant-based plastics (PLA).
2. **Design**: Introduce a modular design for easy refilling and cleaning.
3. **Functionality**: Incorporate a built-in water filter for purification.
4. **Durability**: Enhance the bottle's lifespan through robust construction.
5. **User-friendliness**: Simplify the cap mechanism for easy opening and closing.

These changes would significantly reduce plastic waste, promote recycling, ensure access to clean drinking water, and enhance the overall user experience.

Now, I will detail each change and its benefits in a structured format.</think>

<response>### Redesign of the Plastic Water Bottle for Sustainability and User-Friendliness

#### 1. Material: Biodegradable or Recyclable Alternatives

**Change**: Transition from traditional PET plastic to glass or plant-based plastics (Polylactic Acid - PLA).

**Benefits**:
- **Sustainability**: Glass and PLA are biodegradable or highly recyclable, drastically reducing plastic pollution.
- **Health**: Unlike PET, these materials do not leach chemicals into the water, ensuring safer consumption.

#### 2. Modular Design for Easy Refilling and Cleaning

**Change**: Implement a detachable, interchangeable inner liner within a reusable outer casing.

**Benefits**:
- **User-Friendliness**: Users can easily remove the inner liner for thorough cleaning, reducing the risk of bacterial growth.
- **Sustainability**: The outer casing remains intact, encouraging reuse, while the inner liner can be replaced or recycled when worn out.

#### 3. Built-in Water Filter

**Change**: Integrate a removable, replaceable water filter into the bottle cap.

**Benefits**:
- **Accessibility**: Provides clean drinking water directly from any source (tap, river, etc.), eliminating the need for additional filtration devices.
- **Health**: Removes contaminants, bacteria, and impurities, ensuring safe hydration.
- **Sustainability**: Reduces the use of single-use plastic water bottles by offering a purification solution within a reusable container.

#### 4. Enhanced Durability

**Change**: Use high-quality, durable materials and robust construction techniques for both the outer casing and inner liner.

**Benefits**:
- **Longevity**: A more robust design increases the bottle's lifespan, reducing the frequency of replacements.
- **Cost-effectiveness**: Although the initial cost might be higher, the long-term savings from reduced replacements make it economical.
- **Sustainability**: Less frequent disposal means lower environmental impact.

#### 5. Simplified Cap Mechanism

**Change**: Adopt a one-touch, easy-to-open and close cap design, possibly inspired by sports bottle caps.

**Benefits**:
- **User-Friendliness**: Especially beneficial for children, elderly, or those with limited hand dexterity.
- **Convenience**: Quick access to water encourages more frequent hydration, promoting healthier habits.

### Conclusion

This redesigned water bottle addresses key sustainability concerns by minimizing plastic use and waste, while also enhancing user-friendliness through improved functionality, durability, and accessibility. By integrating biodegradable materials, a modular design, a built-in filter, robust construction, and a simple cap mechanism, the bottle not only reduces environmental footprint but also offers a superior user experience.</response>
  • thinking=False
Item for Redesign: Plastic Bottle (e.g., water or beverage bottle)

Redesign Concept: Eco-Friendly, Modular, and Multi-Functional Reusable Bottle

Changes:

1. Material: Replace the conventional plastic with food-grade, BPA-free, and recyclable materials such as stainless steel or glass. These materials are durable, non-toxic, and have a longer lifespan, reducing waste.

2. Modular Design: Introduce a modular design that allows users to customize their bottle according to their needs. This could include interchangeable caps, mouthpiece sizes, and carrying loops. Users can purchase additional modules as needed, promoting a more sustainable approach by reducing the need to buy an entirely new bottle for different purposes.

3. Integrated Filter: Incorporate a built-in, washable, and reusable filter that can remove impurities and improve the taste of water. This eliminates the need for single-use disposable filters or bottled water, further reducing plastic waste.

4. Smart Cap: Develop a smart cap with a built-in digital display and temperature sensor. This feature allows users to track their daily water intake, set hydration goals, and monitor the temperature of their beverage. The smart cap can be synced with a mobile app for additional functionality, such as reminders and progress tracking.

5. Easy-to-Clean Design: Ensure the bottle has a wide mouth and smooth interior surfaces for easy cleaning. Include a brush for hard-to-reach areas, making maintenance simple and encouraging regular use.

6. Collapsible Structure: Implement a collapsible design that reduces the bottle's volume when not in use, making it more portable and convenient for storage.

Benefits:

1. Sustainability: By using recyclable materials and reducing plastic waste, this redesigned bottle significantly contributes to a more sustainable lifestyle. The modular design and reusable filter also minimize single-use plastic consumption.

2. User-Friendly: The smart cap, easy-to-clean design, and collapsible structure make the bottle convenient and user-friendly. Users can customize their bottle to suit their needs, ensuring a better overall experience.

3. Healthier Option: Using food-grade, BPA-free materials and an integrated filter ensures that the beverages consumed are free from harmful chemicals and impurities, promoting a healthier lifestyle.

4. Cost-Effective: Although the initial investment might be higher, the long-term savings from reduced purchases of single-use plastic bottles and disposable filters make this reusable bottle a cost-effective choice.

5. Encourages Hydration: The smart cap's features, such as hydration tracking and temperature monitoring, can motivate users to stay hydrated and develop healthier habits.

By redesigning a common household item like the plastic bottle, we can create a more sustainable, user-friendly, and health-conscious alternative that benefits both individuals and the environment.

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and has established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI concerns here.