--- pipeline_tag: text-generation inference: false license: apache-2.0 library_name: transformers tags: - language - granite-3.2 - ganite base_model: - ibm-granite/granite-3.2-8b-instruct --- # Granite-3.2-8B-Instruct **Model Summary:** Granite-3.2-8B-Instruct is an 8-billion-parameter, long-context AI model fine-tuned for thinking capabilities. Built on top of [Granite-3.1-8B-Instruct](https://huggingface.co/ibm-granite/granite-3.1-8b-instruct), it has been trained using a mix of permissively licensed open-source datasets and internally generated synthetic data designed for reasoning tasks. The model allows controllability of its thinking capability, ensuring it is applied only when required. - **Developers:** Granite Team, IBM - **Website**: [Granite Docs](https://www.ibm.com/granite/docs/) - **Release Date**: February 26th, 2025 - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-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-3.2-8B-Instruct model. Install the following libraries: ```shell 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. ```python from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed import torch model_path="ibm-granite/granite-3.2-8b-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":"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) ``` **Example Outputs** - thinking=True ```md Here is my thought process: 1. We know we start with 10 liters of a 30% acid solution, so there's 3 liters of pure acid in it (10 liters * 0.3). 2. We need to determine how much of the 70% acid solution to add such that the final mixture is 50% acid. 3. Let's say x liters of the 70% acid solution are added. This will contribute 0.7x liters of pure acid. 4. The total volume of the new mixture will be 10 + x liters, and the total amount of pure acid will be 3 + 0.7x liters. 5. We need to set up an equation where (3 + 0.7x) / (10 + x) = 0.5 (since we want a 50% acid mixture). 6. Solving this equation for x will give us the volume of 70% solution needed. Here is my response: To solve this, we need to set up an equation based on the concentration of acid before and after mixing. 1. **Initial Acid Content**: - We start with 10 liters of a 30% acid solution. - Pure acid in this = 10 * 0.3 = 3 liters. 2. **Variable for Addition**: - Let x be the liters of 70% acid solution to be added. - Pure acid in x liters of 70% solution = 0.7x liters. 3. **Final Mixture Concentration**: - Total volume of mixture = 10 + x liters. - Total pure acid in the mixture = 3 (from initial solution) + 0.7x (from added solution). 4. **Setting up the equation for 50% acid concentration**: - We require that the ratio of pure acid to total volume is 0.5 (50%). - Therefore, the equation is: \[ \frac{3 + 0.7x}{10 + x} = 0.5 \] 5. **Solving the equation**: Multiply both sides by (10 + x) to clear the fraction: \[ 3 + 0.7x = 0.5(10 + x) \] Expanding the right side: \[ 3 + 0.7x = 5 + 0.5x \] Subtract 0.5x from both sides: \[ 3 + 0.2x = 5 \] Subtract 3 from both sides: \[ 0.2x = 2 \] Divide by 0.2: \[ x = 10 \] So, 10 liters of the 70% acid solution must be added to the initial 10 liters of 30% solution to get a 50% acid mixture. Let's verify: - Initial acid: 3 liters - Acid from added solution: 0.7 * 10 = 7 liters - Total acid: 3 + 7 = 10 liters - Total volume: 10 + 10 = 20 liters - Acid percentage: \(\frac{10}{20} = 0.5 = 50\%\) This confirms our solution. Final answer: 10 liters of 70% acid solution should be added. ``` - thinking=False ```md Let's denote the amount of 70% acid solution to be added as x liters. We start with 10 liters of a 30% acid solution, which means there are 0.3 * 10 = 3 liters of pure acid in it. We want to end up with a 50% acid solution after adding x liters of 70% acid solution. The total volume of the mixture will be 10 + x liters, and we want half of this volume to be pure acid. So, the amount of pure acid in the final mixture should be 0.5 * (10 + x) liters. The amount of pure acid in the final mixture comes from two sources: the original 30% solution and the added 70% solution. So, we can set up the following equation: 3 (from the original solution) + 0.7x (from the added solution) = 0.5 * (10 + x) Now, let's solve for x: 3 + 0.7x = 5 + 0.5x 0.7x - 0.5x = 5 - 3 0.2x = 2 x = 2 / 0.2 x = 10 So, you need to add 10 liters of a 70% acid solution to the 10 liters of a 30% acid solution to get a 50% acid mixture. ``` **Evaluation Results:**
Models ArenaHard Alpaca-Eval-2 MMLU PopQA TruthfulQA BigBenchHard DROP GSM8K HumanEval HumanEval+ IFEval AttaQ
Llama-3.1-8B-Instruct 36.43 27.22 69.15 28.79 52.79 72.66 61.48 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 65.71 44.46 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 70.40 54.71 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 65.04 42.76 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 68.55 50.78 79.15 89.63 85.79 73.20 85.73
Granite-3.1-2B-Instruct 23.3 27.17 57.11 20.55 59.79 54.46 18.68 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 52.27 21.12 67.02 80.13 73.39 61.55 83.23
Granite-3.2-8B-Instruct 55.25 61.19 66.79 28.04 66.92 64.77 50.95 81.65 89.35 85.72 74.31 85.42
**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 capabilites. **Infrastructure:** We train Granite-3.2-8B-Instruct 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-3.2-8B-Instruct builds upon Granite-3.1-8B-Instruct, leveraging 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-3.1-8B-Instruct](https://huggingface.co/ibm-granite/granite-3.1-8b-instruct) remain relevant. **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