granite-3.3

Model Summary: Granite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities. Built on top of Granite-3.3-8B-Base, the model delivers significant gains on benchmarks for measuring generic performance including AlpacaEval-2.0 and Arena-Hard, and improvements in mathematics, coding, and instruction following. It supports structured reasoning through \ and \ tags, providing clear separation between internal thoughts and final outputs. The model has been trained on a carefully balanced combination of permissively licensed data and curated synthetic tasks.

• Developers: Granite Team, IBM
• Website: Granite Docs
• Release Date: April 16th, 2025
• License: Apache 2.0

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.

Intended Use: This model is designed to handle general instruction-following tasks and can be integrated into AI assistants across various domains, including business applications.

Capabilities

• Thinking

• Summarization

• Text classification

• Text extraction

• Question-answering

• Retrieval Augmented Generation (RAG)

• Code related tasks

• Function-calling tasks

• Multilingual dialog use cases

• Long-context tasks including long document/meeting summarization, long document QA, etc.

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

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.

#### 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 constructi