--- title: granite-3.2-2b-instruct canonical_url: "https://www.modelscope.cn/models/ibm-granite/granite-3.2-2b-instruct" md_url: "https://www.modelscope.cn/models/ibm-granite/granite-3.2-2b-instruct.md" repository: ibm-granite/granite-3.2-2b-instruct last_updated: 2025-04-24 license: apache-2.0 pipeline_tag: text-generation tasks: - text-generation model_type: - granite architectures: - GraniteForCausalLM base_model: - ibm-granite/granite-3.1-2b-instruct base_model_relation: finetune parameters: 2.5B tensor_type: - BF16 library_name: - pytorch - transformer - safetensors frameworks: - pytorch inference_backends: - "deploy_task text/emb" - "sglang 0.5.2" - "vllm 0.9.2" downloads: 745 stars: 0 tags: - language - granite-3.2 --- # granite-3.2-2b-instruct > granite-3.2-2b-instruct - ibm-granite 在 ModelScope 开源的模型。Granite-3.2-2B-Instruct ibm-granite/granite-3.2-2b-instruct 是 ModelScope 魔搭社区上的 2.5B 参数text-generation模型，采用 apache-2.0 许可，基于 ibm-granite/granite-3.1-2b-instruct 构建，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。 - **Repository**: ibm-granite/granite-3.2-2b-instruct - **License**: apache-2.0 - **Tasks**: text-generation - **Parameters**: 2.5B - **Base model**: ibm-granite/granite-3.1-2b-instruct - **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2 - **Tags**: language, granite-3.2 - **Downloads**: 745 - **Stars**: 0 - **Last updated**: 2025-04-24 Source: https://www.modelscope.cn/models/ibm-granite/granite-3.2-2b-instruct --- # Granite-3.2-2B-Instruct **Model Summary:** Granite-3.2-2B-Instruct is an 2-billion-parameter, long-context AI model fine-tuned for thinking capabilities. Built on top of [Granite-3.1-2B-Instruct](https://huggingface.co/ibm-granite/granite-3.1-2b-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-3.2-2B-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-3.2-2b-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. First, let's understand the composition of the initial 10 liters of 30% acid solution: - Acid content = 30% of 10 liters = 0.30 * 10 = 3 liters 2. We want to end up with a 50% acid solution. Let's denote the volume of the 70% acid solution to be added as 'x' liters. 3. The amount of acid in the final mixture (50% solution) should equal the initial acid content plus the acid from the added 70% solution. - Total acid in final mixture = 0.50 * (10 + x) 4. The equation representing the total acid content is: 3 (from initial solution) + 0.70 * x (from added solution) = 0.50 * (10 + x) 5. Now, we solve for 'x': 3 + 0.70x = 5 + 0.50x 0.70x - 0.50x = 5 - 3 0.20x = 2 x = 2 / 0.20 x = 10 liters 6. Therefore, 10 liters of a 70% acid solution must be added to the initial 10 liters of 30% acid solution to achieve a 50% acid mixture. Here is my response: To solve this problem, we need to determine how much of a 70% acid solution must be added to a 10-liter solution that is already 30% acid to create a new mixture that is 50% acid. Here's how to calculate it: 1. **Initial Acid Content**: - The initial 10-liter solution contains 3 liters of acid (since 30% of 10 liters). 2. **Desired Final Acid Content**: - We want the final mixture to be 50% acid. 3. **Equation Setup**: - Let 'x' be the volume (in liters) of the 70% acid solution to be added. - The equation representing the total acid content in the final mixture (which is 10 liters from the initial solution plus 'x' liters of the added solution) should equal 50% of the total volume (10 + x). - This gives us: 3 (acid from initial solution) + 0.70x (acid from added solution) = 0.50(10 + x) 4. **Solving the Equation**: - First, simplify the right side of the equation: 0.50(10 + x) = 5 + 0.50x - Now, the equation is: 3 + 0.70x = 5 + 0.50x - Subtract 0.50x from both sides: 0.20x = 2 - Divide both sides by 0.20: x = 2 / 0.20 - x = 10 liters 5. **Conclusion**: - To achieve a 50% acid mixture from the initial 30% solution, you need to add 10 liters of a 70% acid solution. So, the final answer is that 10 liters of a 70% acid solution must be added to the initial 10 liters of 30% acid solution. ``` - thinking=False ```md To solve this problem, we'll use the concept of volume and concentration. Let's denote the amount of 70% acid solution we need to add as "x" liters. First, let's find out how much acid is in the initial 10-liter solution: Acid in initial solution = 30% of 10 liters = 0.30 * 10 = 3 liters Now, we want to end up with a 50% acid solution in a total volume of (10 + x) liters. Let's denote the final volume as V. Final acid concentration = 50% Final acid amount = 50% of V = 0.50 * V We know the initial acid amount and the final acid amount, so we can set up an equation: Initial acid amount + Acid from added solution = Final acid amount 3 liters + (70% of x) = 0.50 * (10 + x) Now, let's solve for x: 0.70x + 3 = 0.50 * 10 + 0.50x 0.70x - 0.50x = 0.50 * 10 - 3 0.20x = 5 - 3 0.20x = 2 x = 2 / 0.20 x = 10 liters So, you need to add 10 liters of a 70% acid solution to the initial 10-liter 30% acid solution to achieve 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-3.2-8B-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
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
**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-3.2-2B-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-3.2-2B-Instruct builds upon Granite-3.1-2B-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-3.1-2B-Instruct](https://huggingface.co/ibm-granite/granite-3.1-2b-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