granite-4.0-tiny-preview

mof-class3-qualified

Granite-4.0-Tiny-Preview#

Model Summary: Granite-4-Tiny-Preview is a 7B parameter fine-grained hybrid mixture-of-experts (MoE) instruct model fine-tuned from Granite-4.0-Tiny-Base-Preview using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets tailored for solving long context problems. This model is developed using a diverse set of techniques with a structured chat format, including supervised fine-tuning, and model alignment using reinforcement learning.

• Developers: Granite Team, IBM
• Website: Granite Docs
• Release Date: May 2nd, 2025
• License: Apache 2.0

Supported Languages: English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. However, users may fine-tune 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.

Installation: You need to install transformer from source to use this checkpoint.

HuggingFace PR: https://github.com/huggingface/transformers/pull/37658

Install transformer from source: https://huggingface.co/docs/transformers/en/installation#install-from-source

Generation: After installation, copy the code snippet below to run the example.

from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
import torch

model_path="ibm-granite/granite-4.0-tiny-preview"
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":"You have 10 liters of a 30% acid solution. How many liters of a 70% acid solution must be added to achieve a 50% acid mixture?"}]

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)

Evaluation Results:

Comparison with previous granite models1. Scores of AlpacaEval-2.0 and Arena-Hard are calculated with thinking=True

| Models | Arena-Hard | AlpacaEval-2.0 | MMLU | PopQA | TruthfulQA | BigBenchHard | DROP | GSM8K | HumanEval | HumanEval+ | IFEval | AttaQ

| Granite-3.3-2B-Instruct | 28.86 | 43.45 | 55.88 | 18.4 | 58.97 | 52.51 | 35.98 | 72.48 | 80.51 | 75.68 | 65.8 | 87.47

| Granite-3.3-8B-Instruct | 57.56 | 62.68 | 65.54 | 26.17 | 66.86 | 59.01 | 41.53 | 80.89 | 89.73 | 86.09 | 74.82 | 88.5

| Granite-4.0-Tiny-Preview | 26.70 | 35.16 | 60.40 | 22.93 | 58.07 | 55.71 | 46.22 | 70.05 | 82.41 | 78.33 | 63.03 | 86.10

Training Data: Overall, our training data is largely comprised of two key sources: (1) publicly available datasets with permissive license, (2) internal synthetically generated data targeted to enhance reasoning capabilities.

Infrastructure: We train Granite-4.0-Tiny-Preview using IBM's super computing cluster, Blue Vela, which is outfitted with NVIDIA H100 GPUs. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs.

Ethical Considerations and Limitations: Granite-4.0-Tiny-Preview, leverages both permissively licensed open-source and select proprietary data for enhanced performance. Since it inherits its foundation from the previous model, all ethical considerations and limitations applicable to Granite-4.0-Tiny-Preview remain relevant.

Signature verification: Model signing is an experimental feature with ongoing development, which might include breaking changes. We are releasing these capabilities to improve the integrity of our models for our security-conscious users and to facilitate feedback from the community.

Before trying to verify the signature, ensure that the tensor files have been downloaded with git-lfs and that no files have been added, removed, or modified in your local git checkout:

  git lfs fetch --all
  git lfs pull
  git lfs checkout

Install the model_signing (v1.0.1) library with the following command:

   pip install 'model-signing==v1.1.1'

Then verify the signature with the following command ensuring that the IBM identity 'granite.preview@ibm.com' was used for signing this model:

   python -m model_signing verify sigstore \
     --signature model.sig \
     --ignore-paths .git \
     --ignore-paths .gitattributes \
     --identity Granite.Preview@ibm.com \
     --identity_provider https://sigstore.verify.ibm.com/oauth2 \
     .

Resources

• ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
• 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
• 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources