File size: 18,339 Bytes
b1ece2b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 |
---
pipeline_tag: text-generation
inference: false
license: apache-2.0
library_name: transformers
tags:
- language
- granite-3.2
- ganite
base_model:
- ibm-granite/granite-3.2-2b-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:**
<table>
<thead>
<tr>
<th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
<th style="text-align:center; background-color: #001d6c; color: white;">ArenaHard</th>
<th style="text-align:center; background-color: #001d6c; color: white;">Alpaca-Eval-2</th>
<th style="text-align:center; background-color: #001d6c; color: white;">MMLU</th>
<th style="text-align:center; background-color: #001d6c; color: white;">PopQA</th>
<th style="text-align:center; background-color: #001d6c; color: white;">TruthfulQA</th>
<th style="text-align:center; background-color: #001d6c; color: white;">BigBenchHard</th>
<th style="text-align:center; background-color: #001d6c; color: white;">DROP</th>
<th style="text-align:center; background-color: #001d6c; color: white;">GSM8K</th>
<th style="text-align:center; background-color: #001d6c; color: white;">HumanEval</th>
<th style="text-align:center; background-color: #001d6c; color: white;">HumanEval+</th>
<th style="text-align:center; background-color: #001d6c; color: white;">IFEval</th>
<th style="text-align:center; background-color: #001d6c; color: white;">AttaQ</th>
</tr></thead>
<tbody>
<tr>
<td style="text-align:left; background-color: #DAE8FF; color: black;">Llama-3.1-8B-Instruct</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">36.43</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">27.22</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">69.15</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">28.79</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">52.79</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">72.66</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">61.48</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">83.24</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">85.32</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">80.15</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">79.10</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">83.43</td>
</tr>
<tr>
<td style="text-align:left; background-color: #DAE8FF; color: black;">DeepSeek-R1-Distill-Llama-8B</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">17.17</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">21.85</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">45.80</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">13.25</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">47.43</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">65.71</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">44.46</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">72.18</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">67.54</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">62.91</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">66.50</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">42.87</td>
</tr>
<tr>
<td style="text-align:left; background-color: #DAE8FF; color: black;">Qwen-2.5-7B-Instruct</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">25.44</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">30.34</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">74.30</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">18.12</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">63.06</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">70.40</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">54.71</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">84.46</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">93.35</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">89.91</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">74.90</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">81.90</td>
</tr>
<tr>
<td style="text-align:left; background-color: #DAE8FF; color: black;">DeepSeek-R1-Distill-Qwen-7B</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">10.36</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">15.35</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">50.72</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">9.94</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">47.14</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">65.04</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">42.76</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">78.47</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">79.89</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">78.43</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">59.10</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">42.45</td>
</tr>
<tr>
<td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-8B-Instruct</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">37.58</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">30.34</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">66.77</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">28.7</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">65.84</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">68.55</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">50.78</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">79.15</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">89.63</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">85.79</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">73.20</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">85.73</td>
</tr>
<tr>
<td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-2B-Instruct</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">23.3</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">27.17</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">57.11</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">20.55</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">59.79</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">54.46</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">18.68</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">67.55</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">79.45</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">75.26</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">63.59</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">84.7</td>
</tr>
<tr>
<td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.2-2B-Instruct</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">24.86</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">34.51</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">57.18</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">20.56</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">59.8</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">52.27</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">21.12</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">67.02</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">80.13</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">73.39</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">61.55</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">83.23</td>
</tr>
<tr>
<td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.2-8B-Instruct</b></td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">55.25</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">61.19</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">66.79</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">28.04</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">66.92</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">64.77</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">50.95</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">81.65</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">89.35</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">85.72</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">74.31</td>
<td style="text-align:center; background-color: #DAE8FF; color: black;">85.42</td>
</tr>
</tbody></table>
**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.
<!-- A detailed attribution of datasets can be found in [Granite 3.2 Technical Report (coming soon)](#), and [Accompanying Author List](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/author-ack.pdf). -->
**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
<!-- ## Citation
```
@misc{granite-models,
author = {author 1, author2, ...},
title = {},
journal = {},
volume = {},
year = {2024},
url = {https://arxiv.org/abs/0000.00000},
}
``` --> |