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, 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.
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.
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-3.2-2b-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
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
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.
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 remain relevant.
import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("ibm-granite/granite-3.2-2b-instruct", revision="641593c3b25bec0b1efe9f0f7d7a67f7243f86a3")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-3.2-2b-instruct", revision="641593c3b25bec0b1efe9f0f7d7a67f7243f86a3", device_map="auto")