few formatting and unifying MATH Lvl-5 label

README.md

@@ -6,37 +6,33 @@ language:
 - pt
 tags:
 - falcon3
-license: other
-license_name: falcon-llm-license
+license: other 
+license_name: falcon-llm-license 
 license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
-library_name: transformers
 ---
 
-<div align="center">
-    <img src="https://huggingface.co/datasets/tiiuae/documentation-images/resolve/main/general/falco3-logo.png" alt="drawing" width="500"/>
-</div>
 
 # Falcon3-3B-Base
 
-**Falcon3** family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters.
+**Falcon3** family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B.
 
 This repository contains the **Falcon3-3B-Base**. It achieves strong results on reasoning, language understanding, instruction following, code and mathematics tasks.
-Falcon3-3B-Base supports 4 languages (English, French, Spanish, Portuguese) and a context length of up to 8K.
-It was pruned in terms of depth and width from Falcon3-7B-Base and was efficiently trained on only 100 GT using a knowledge distillation objective.
+Falcon3-3B-Base supports 4 languages (english, french, spanish, portuguese) and a context length up to 8K.
+Falcon3-3B-Base pruned (depth + width) from Falcon3-7B-Base, was effeciently trained on only 100 GT using a knowledge distillation objective.
 
 ⚠️ **This is a raw, pretrained model, which should be further finetuned using SFT, RLHF, continued pretraining, etc. for most use cases.** 
 
 ## Model Details
 - Architecture
-  - Transformer-based causal decoder-only architecture
+  - Transformer based causal decoder only architecture
   - 22 decoder blocks
-  - Grouped Query Attention (GQA) for faster inference: 12 query heads and 4 key-value heads
+  - Grouped query attention (GQA) for faster inference: 12 query heads and 4 KV heads
   - Wider head dimension: 256
   - High RoPE value to support long context understanding: 1000042
-  - Uses SwiGLU and RMSNorm
+  - Uses SwiGLu and RMSNorm
   - 8K context length
   - 131K vocab size
-- Pruned and healed from Falcon3-7B-Base on only 100 Gigatokens of datasets comprising of web, code, STEM, high quality and mutlilingual data using 1024 H100 GPU chips
+- Pruned and Healed from Falcon3-7B-Base on only 100 Gigatokens of datasets comprising of web, code, STEM, high quality and mutlilingual data using 2048 H100 GPU chips
 - Supports EN, FR, ES, PT
 - Developed by [Technology Innovation Institute](https://www.tii.ae)
 - License: TII Falcon-LLM License 2.0
@@ -67,10 +63,7 @@ print(response[0]['generated_text'])
 <br>
 
 ## Benchmarks
-We report in the following table our internal pipeline benchmarks.
- - We use [lm-evaluation harness](https://github.com/EleutherAI/lm-evaluation-harness).
- - We report **raw scores**.
- - We use same batch-size across all models.
+We report in the following table our internal pipeline benchmarks:
 
 
 
@@ -99,74 +92,74 @@ We report in the following table our internal pipeline benchmarks.
             <td>MMLU (5-shot)</td>
             <td>56.1</td>
             <td><b>65.6</b></td>
-            <td>58.7</td>
+            <td>58.6</td>
             <td>55.5</td>
         </tr>
         <tr>
             <td>MMLU-PRO (5-shot)</td>
             <td>24.9</td>
-            <td><b>32</b></td>
-            <td>26.2</td>
-            <td>28.8</td>
+            <td><b>31.99</b></td>
+            <td>26.21</td>
+            <td>28.77</td>
         </tr>
         <tr>
             <td>IFEval</td>
-            <td>12.8</td>
-            <td>27</td>
-            <td>22.8</td>
-            <td><b>27.7</b></td>
+            <td>12.83</td>
+            <td>27.0</td>
+            <td>22.81</td>
+            <td><b>27.67</b></td>
         </tr>
         <tr>
             <td rowspan="2">Math</td>
             <td>GSM8K (5-shot)</td>
-            <td>26.7</td>
-            <td><b>69</b></td>
+            <td>26.68</td>
+            <td><b>68.99</b></td>
             <td>25.7</td>
-            <td>63.9</td>
+            <td>63.91</td>
         </tr>
         <tr>
             <td>MATH Lvl-5 (4-shot)</td>
-            <td>1.4</td>
-            <td>8.4</td>
-            <td>1.7</td>
-            <td><b>9.4</b></td>
+            <td>1.39</td>
+            <td>8.43</td>
+            <td>1.73</td>
+            <td><b>9.38</b></td>
         </tr>
         <tr>
             <td rowspan="4">Reasoning</td>
             <td>Arc Challenge (25-shot)</td>
-            <td>50.8</td>
-            <td><b>55.5</b></td>
-            <td>50.3</td>
-            <td>54.9</td>
+            <td>50.76</td>
+            <td><b>55.54</b></td>
+            <td>50.34</td>
+            <td>54.86</td>
         </tr>
         <tr>
             <td>GPQA (0-shot)</td>
-            <td>27.5</td>
-            <td>27.5</td>
-            <td>28.6</td>
-            <td><b>31.2</b></td>
+            <td>27.49</td>
+            <td>27.53</td>
+            <td><b>38.6</b></td>
+            <td>31.15</td>
         </tr>
         <tr>
             <td>MUSR (0-shot)</td>
-            <td>35.2</td>
-            <td><b>43</b></td>
-            <td>42.1</td>
+            <td>35.24</td>
+            <td><b>43.03</b></td>
+            <td>42.13</td>
             <td>37.5</td>
         </tr>
         <tr>
             <td>BBH (3-shot)</td>
-            <td>38.6</td>
-            <td><b>46.1</b></td>
-            <td>40.9</td>
-            <td>44.2</td>
+            <td>38.59</td>
+            <td><b>46.12</b></td>
+            <td>40.85</td>
+            <td>44.23</td>
         </tr>
         <tr>
             <td rowspan="4">CommonSense Understanding</td>
             <td>PIQA (0-shot)</td>
-            <td>77.4</td>
-            <td><b>78.9</b></td>
-            <td>78.3</td>
-            <td>75.6</td>
+            <td>77.42</td>
+            <td><b>78.89</b></td>
+            <td>78.29</td>
+            <td>75.62</td>
         </tr>
         <tr>
             <td>SciQ (0-shot)</td>
@@ -177,16 +170,16 @@ We report in the following table our internal pipeline benchmarks.
         </tr>
         <tr>
             <td>Winogrande (0-shot)</td>
-            <td><b>69.7</b></td>
-            <td>68.8</td>
-            <td>68.4</td>
-            <td>64.6</td>
+            <td><b>69.69</b></td>
+            <td>68.82</td>
+            <td>68.35</td>
+            <td>64.64</td>
         </tr>
         <tr>
             <td>OpenbookQA (0-shot)</td>
             <td><b>43.2</b></td>
             <td>42.2</td>
-            <td>43</td>
+            <td>43.0</td>
             <td>39.4</td>
         </tr>
     </tbody>
@@ -201,11 +194,10 @@ Coming soon....
 
 ## Citation
 If the Falcon3 family of models were helpful to your work, feel free to give us a cite.
- 
+
 ```
 @misc{Falcon3,
     title = {The Falcon 3 Family of Open Models},
-    url = {https://huggingface.co/blog/falcon3},
     author = {Falcon-LLM Team},
     month = {December},
     year = {2024}