adding model card
Browse files
README.md
CHANGED
|
@@ -1,3 +1,349 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: text-generation
|
| 3 |
+
inference: false
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- language
|
| 8 |
+
- granite-3.2
|
| 9 |
+
base_model:
|
| 10 |
+
- ibm-granite/granite-3.1-2b-instruct
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Granite-3.2-2B-Instruct
|
| 14 |
+
|
| 15 |
+
**Model Summary:**
|
| 16 |
+
Granite-3.2-2B-Instruct is an 2-billion-parameter, long-context AI model fine-tuned for advanced reasoning 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.
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
- **Developers:** Granite Team, IBM
|
| 20 |
+
- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/)
|
| 21 |
+
- **Release Date**: February 21th, 2025
|
| 22 |
+
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
|
| 23 |
+
|
| 24 |
+
**Supported Languages:**
|
| 25 |
+
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.
|
| 26 |
+
|
| 27 |
+
**Intended Use:**
|
| 28 |
+
This model is designed to handle general instruction-following tasks and can be integrated into AI assistants across various domains, including business applications.
|
| 29 |
+
|
| 30 |
+
**Capabilities**
|
| 31 |
+
* **Thinking**
|
| 32 |
+
* Summarization
|
| 33 |
+
* Text classification
|
| 34 |
+
* Text extraction
|
| 35 |
+
* Question-answering
|
| 36 |
+
* Retrieval Augmented Generation (RAG)
|
| 37 |
+
* Code related tasks
|
| 38 |
+
* Function-calling tasks
|
| 39 |
+
* Multilingual dialog use cases
|
| 40 |
+
* Long-context tasks including long document/meeting summarization, long document QA, etc.
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
**Generation:**
|
| 45 |
+
This is a simple example of how to use Granite-3.2-2B-Instruct model.
|
| 46 |
+
|
| 47 |
+
Install the following libraries:
|
| 48 |
+
|
| 49 |
+
```shell
|
| 50 |
+
pip install torch torchvision torchaudio
|
| 51 |
+
pip install accelerate
|
| 52 |
+
pip install transformers
|
| 53 |
+
```
|
| 54 |
+
Then, copy the snippet from the section that is relevant for your use case.
|
| 55 |
+
|
| 56 |
+
```python
|
| 57 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
|
| 58 |
+
import torch
|
| 59 |
+
|
| 60 |
+
model_path="ibm-granite/granite-3.2-2b-instruct"
|
| 61 |
+
device="cuda"
|
| 62 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 63 |
+
model_path,
|
| 64 |
+
device_map=device,
|
| 65 |
+
torch_dtype=torch.bfloat16,
|
| 66 |
+
)
|
| 67 |
+
tokenizer = AutoTokenizer.from_pretrained(
|
| 68 |
+
model_path
|
| 69 |
+
)
|
| 70 |
+
|
| 71 |
+
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?"}]
|
| 72 |
+
|
| 73 |
+
input_ids = tokenizer.apply_chat_template(conv, return_tensors="pt", thinking=True, return_dict=True, add_generation_prompt=True).to(device)
|
| 74 |
+
|
| 75 |
+
set_seed(42)
|
| 76 |
+
output = model.generate(
|
| 77 |
+
**input_ids,
|
| 78 |
+
max_new_tokens=8192,
|
| 79 |
+
)
|
| 80 |
+
|
| 81 |
+
prediction = tokenizer.decode(output[0, input_ids["input_ids"].shape[1]:], skip_special_tokens=True)
|
| 82 |
+
print(prediction)
|
| 83 |
+
```
|
| 84 |
+
|
| 85 |
+
**Example Outputs**
|
| 86 |
+
- thinking=True
|
| 87 |
+
```md
|
| 88 |
+
Here is my thought process:
|
| 89 |
+
|
| 90 |
+
1. First, let's understand the composition of the initial 10 liters of 30% acid solution:
|
| 91 |
+
- Acid content = 30% of 10 liters = 0.30 * 10 = 3 liters
|
| 92 |
+
|
| 93 |
+
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.
|
| 94 |
+
|
| 95 |
+
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.
|
| 96 |
+
- Total acid in final mixture = 0.50 * (10 + x)
|
| 97 |
+
|
| 98 |
+
4. The equation representing the total acid content is:
|
| 99 |
+
3 (from initial solution) + 0.70 * x (from added solution) = 0.50 * (10 + x)
|
| 100 |
+
|
| 101 |
+
5. Now, we solve for 'x':
|
| 102 |
+
3 + 0.70x = 5 + 0.50x
|
| 103 |
+
0.70x - 0.50x = 5 - 3
|
| 104 |
+
0.20x = 2
|
| 105 |
+
x = 2 / 0.20
|
| 106 |
+
x = 10 liters
|
| 107 |
+
|
| 108 |
+
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.
|
| 109 |
+
|
| 110 |
+
Here is my response:
|
| 111 |
+
|
| 112 |
+
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:
|
| 113 |
+
|
| 114 |
+
1. **Initial Acid Content**:
|
| 115 |
+
- The initial 10-liter solution contains 3 liters of acid (since 30% of 10 liters).
|
| 116 |
+
|
| 117 |
+
2. **Desired Final Acid Content**:
|
| 118 |
+
- We want the final mixture to be 50% acid.
|
| 119 |
+
|
| 120 |
+
3. **Equation Setup**:
|
| 121 |
+
- Let 'x' be the volume (in liters) of the 70% acid solution to be added.
|
| 122 |
+
- 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).
|
| 123 |
+
- This gives us: 3 (acid from initial solution) + 0.70x (acid from added solution) = 0.50(10 + x)
|
| 124 |
+
|
| 125 |
+
4. **Solving the Equation**:
|
| 126 |
+
- First, simplify the right side of the equation: 0.50(10 + x) = 5 + 0.50x
|
| 127 |
+
- Now, the equation is: 3 + 0.70x = 5 + 0.50x
|
| 128 |
+
- Subtract 0.50x from both sides: 0.20x = 2
|
| 129 |
+
- Divide both sides by 0.20: x = 2 / 0.20
|
| 130 |
+
- x = 10 liters
|
| 131 |
+
|
| 132 |
+
5. **Conclusion**:
|
| 133 |
+
- To achieve a 50% acid mixture from the initial 30% solution, you need to add 10 liters of a 70% acid solution.
|
| 134 |
+
|
| 135 |
+
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.
|
| 136 |
+
```
|
| 137 |
+
- thinking=False
|
| 138 |
+
```md
|
| 139 |
+
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.
|
| 140 |
+
|
| 141 |
+
First, let's find out how much acid is in the initial 10-liter solution:
|
| 142 |
+
|
| 143 |
+
Acid in initial solution = 30% of 10 liters = 0.30 * 10 = 3 liters
|
| 144 |
+
|
| 145 |
+
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.
|
| 146 |
+
|
| 147 |
+
Final acid concentration = 50%
|
| 148 |
+
Final acid amount = 50% of V = 0.50 * V
|
| 149 |
+
|
| 150 |
+
We know the initial acid amount and the final acid amount, so we can set up an equation:
|
| 151 |
+
|
| 152 |
+
Initial acid amount + Acid from added solution = Final acid amount
|
| 153 |
+
3 liters + (70% of x) = 0.50 * (10 + x)
|
| 154 |
+
|
| 155 |
+
Now, let's solve for x:
|
| 156 |
+
|
| 157 |
+
0.70x + 3 = 0.50 * 10 + 0.50x
|
| 158 |
+
0.70x - 0.50x = 0.50 * 10 - 3
|
| 159 |
+
0.20x = 5 - 3
|
| 160 |
+
0.20x = 2
|
| 161 |
+
x = 2 / 0.20
|
| 162 |
+
x = 10 liters
|
| 163 |
+
|
| 164 |
+
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.
|
| 165 |
+
```
|
| 166 |
+
|
| 167 |
+
**Evaluation Results:**
|
| 168 |
+
<table>
|
| 169 |
+
|
| 170 |
+
<thead>
|
| 171 |
+
<tr>
|
| 172 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
|
| 173 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">ArenaHard</th>
|
| 174 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">Alpaca-Eval-2</th>
|
| 175 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">MMLU</th>
|
| 176 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">PopQA</th>
|
| 177 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">TruthfulQA</th>
|
| 178 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">BigBenchHard</th>
|
| 179 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">DROP</th>
|
| 180 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">GSM8K</th>
|
| 181 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">HumanEval</th>
|
| 182 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">HumanEval+</th>
|
| 183 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">IFEval</th>
|
| 184 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">AttaQ</th>
|
| 185 |
+
</tr></thead>
|
| 186 |
+
<tbody>
|
| 187 |
+
<tr>
|
| 188 |
+
<td style="text-align:left; background-color: #DAE8FF; color: black;">Llama-3.1-8B-Instruct</td>
|
| 189 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">36.43</td>
|
| 190 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">27.22</td>
|
| 191 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">69.15</td>
|
| 192 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">28.79</td>
|
| 193 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">52.79</td>
|
| 194 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">72.66</td>
|
| 195 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">61.48</td>
|
| 196 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">83.24</td>
|
| 197 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">85.32</td>
|
| 198 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">80.15</td>
|
| 199 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">79.10</td>
|
| 200 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">83.43</td>
|
| 201 |
+
</tr>
|
| 202 |
+
|
| 203 |
+
<tr>
|
| 204 |
+
<td style="text-align:left; background-color: #DAE8FF; color: black;">DeepSeek-R1-Distill-Llama-8B</td>
|
| 205 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">17.17</td>
|
| 206 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">21.85</td>
|
| 207 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">45.80</td>
|
| 208 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">13.25</td>
|
| 209 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">47.43</td>
|
| 210 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">65.71</td>
|
| 211 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">44.46</td>
|
| 212 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">72.18</td>
|
| 213 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">67.54</td>
|
| 214 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">62.91</td>
|
| 215 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">66.50</td>
|
| 216 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">42.87</td>
|
| 217 |
+
</tr>
|
| 218 |
+
|
| 219 |
+
<tr>
|
| 220 |
+
<td style="text-align:left; background-color: #DAE8FF; color: black;">Qwen-2.5-7B-Instruct</td>
|
| 221 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">25.44</td>
|
| 222 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">30.34</td>
|
| 223 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">74.30</td>
|
| 224 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">18.12</td>
|
| 225 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">63.06</td>
|
| 226 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">70.40</td>
|
| 227 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">54.71</td>
|
| 228 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">84.46</td>
|
| 229 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">93.35</td>
|
| 230 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">89.91</td>
|
| 231 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">74.90</td>
|
| 232 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">81.90</td>
|
| 233 |
+
</tr>
|
| 234 |
+
|
| 235 |
+
<tr>
|
| 236 |
+
<td style="text-align:left; background-color: #DAE8FF; color: black;">DeepSeek-R1-Distill-Qwen-7B</td>
|
| 237 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">10.36</td>
|
| 238 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">15.35</td>
|
| 239 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">50.72</td>
|
| 240 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">9.94</td>
|
| 241 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">47.14</td>
|
| 242 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">65.04</td>
|
| 243 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">42.76</td>
|
| 244 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">78.47</td>
|
| 245 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">79.89</td>
|
| 246 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">78.43</td>
|
| 247 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">59.10</td>
|
| 248 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">42.45</td>
|
| 249 |
+
</tr>
|
| 250 |
+
|
| 251 |
+
<tr>
|
| 252 |
+
<td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-8B-Instruct</td>
|
| 253 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">37.58</td>
|
| 254 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">30.34</td>
|
| 255 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">66.77</td>
|
| 256 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">28.7</td>
|
| 257 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">65.84</td>
|
| 258 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">68.55</td>
|
| 259 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">50.78</td>
|
| 260 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">79.15</td>
|
| 261 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">89.63</td>
|
| 262 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">85.79</td>
|
| 263 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">73.20</td>
|
| 264 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">85.73</td>
|
| 265 |
+
</tr>
|
| 266 |
+
|
| 267 |
+
|
| 268 |
+
<tr>
|
| 269 |
+
<td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-2B-Instruct</td>
|
| 270 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">23.3</td>
|
| 271 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">27.17</td>
|
| 272 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">57.11</td>
|
| 273 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">20.55</td>
|
| 274 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">59.79</td>
|
| 275 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">54.46</td>
|
| 276 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">18.68</td>
|
| 277 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">67.55</td>
|
| 278 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">79.45</td>
|
| 279 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">75.26</td>
|
| 280 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">63.59</td>
|
| 281 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">84.7</td>
|
| 282 |
+
</tr>
|
| 283 |
+
|
| 284 |
+
<tr>
|
| 285 |
+
<td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.2-8B-Instruct</td>
|
| 286 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">55.25</td>
|
| 287 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">61.19</td>
|
| 288 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">66.79</td>
|
| 289 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">28.04</td>
|
| 290 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">66.92</td>
|
| 291 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">64.77</td>
|
| 292 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">50.95</td>
|
| 293 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">81.65</td>
|
| 294 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">89.35</td>
|
| 295 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">85.72</td>
|
| 296 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">74.31</td>
|
| 297 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">85.42</td>
|
| 298 |
+
|
| 299 |
+
</tr>
|
| 300 |
+
|
| 301 |
+
<tr>
|
| 302 |
+
<td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.2-2B-Instruct</b></td>
|
| 303 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">24.86</td>
|
| 304 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">34.51</td>
|
| 305 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">57.18</td>
|
| 306 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">20.56</td>
|
| 307 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">59.8</td>
|
| 308 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">52.27</td>
|
| 309 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">21.12</td>
|
| 310 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">67.02</td>
|
| 311 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">80.13</td>
|
| 312 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">73.39</td>
|
| 313 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">61.55</td>
|
| 314 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">83.23</td>
|
| 315 |
+
</tr>
|
| 316 |
+
|
| 317 |
+
|
| 318 |
+
|
| 319 |
+
|
| 320 |
+
|
| 321 |
+
</tbody></table>
|
| 322 |
+
|
| 323 |
+
**Training Data:**
|
| 324 |
+
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.
|
| 325 |
+
<!-- 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). -->
|
| 326 |
+
|
| 327 |
+
**Infrastructure:**
|
| 328 |
+
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.
|
| 329 |
+
|
| 330 |
+
**Ethical Considerations and Limitations:**
|
| 331 |
+
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.
|
| 332 |
+
|
| 333 |
+
|
| 334 |
+
**Resources**
|
| 335 |
+
- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
|
| 336 |
+
- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
|
| 337 |
+
- 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources
|
| 338 |
+
|
| 339 |
+
<!-- ## Citation
|
| 340 |
+
```
|
| 341 |
+
@misc{granite-models,
|
| 342 |
+
author = {author 1, author2, ...},
|
| 343 |
+
title = {},
|
| 344 |
+
journal = {},
|
| 345 |
+
volume = {},
|
| 346 |
+
year = {2024},
|
| 347 |
+
url = {https://arxiv.org/abs/0000.00000},
|
| 348 |
+
}
|
| 349 |
+
``` -->
|