|
--- |
|
language: |
|
- en |
|
- fr |
|
- es |
|
- pt |
|
tags: |
|
- falcon3 |
|
license: other |
|
license_name: falcon-llm-license |
|
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html |
|
--- |
|
|
|
|
|
# Falcon3-7B-Base |
|
|
|
**Falcon3** family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B. |
|
|
|
This repository contains the **Falcon3-7B-Base**. It achieves state of art results (at release's time) on reasoning, language understanding, instruction following, code and mathematics tasks. |
|
Falcon3-7B-Base supports 4 languages (english, french, spanish, portuguese) and a context length up to 32K. |
|
|
|
⚠️ **This is a raw, pretrained model, which should be further finetuned using SFT, RLHF, continued pretraining, etc. for most usecases.** |
|
|
|
## Model Details |
|
- Architecture |
|
- Transformer based causal decoder only architecture |
|
- 28 decoder blocks |
|
- Grouped query attention (GQA) for faster inference: 12 query heads and 4 key value heads |
|
- Wider head dimension: 256 |
|
- High RoPE value to support long context understanding: 1000042 |
|
- Uses SwiGLU and RMSNorm |
|
- 32K context length |
|
- 131K vocab size |
|
- Pretrained on 14 Teratokens 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 |
|
- Model Release Date: December 2024 |
|
|
|
|
|
## Getting started |
|
|
|
<details> |
|
<summary> Click to expand </summary> |
|
|
|
```python |
|
import torch |
|
from transformers import pipeline |
|
|
|
pipe = pipeline( |
|
"text-generation", |
|
model="tiiuae/Falcon3-7B-Base", |
|
torch_dtype=torch.bfloat16, |
|
device_map="auto" |
|
) |
|
response = pipe("Question: How many hours in one day? Answer: ") |
|
print(response[0]['generated_text']) |
|
``` |
|
|
|
</details> |
|
|
|
<br> |
|
|
|
## Benchmarks |
|
We report in the following table our internal pipeline benchmarks: |
|
|
|
|
|
|
|
<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;"> |
|
<colgroup> |
|
<col style="width: 10%;"> |
|
<col style="width: 10%;"> |
|
<col style="width: 7%;"> |
|
<col style="width: 7%;"> |
|
<col style="width: 7%;"> |
|
<col style="background-color: rgba(80, 15, 213, 0.5); width: 7%;"> |
|
</colgroup> |
|
<thead> |
|
<tr> |
|
<th>Category</th> |
|
<th>Benchmark</th> |
|
<th>Llama3.1-8B</th> |
|
<th>Qwen2.5-7B</th> |
|
<th>gemma-2-9b</th> |
|
<th>Falcon3-7B-Base</th> |
|
</tr> |
|
</thead> |
|
<tbody> |
|
<tr> |
|
<td rowspan="3">General</td> |
|
<td>MMLU (5-shot)</td> |
|
<td>65.2</td> |
|
<td><b>74.2</b></td> |
|
<td>70.8</td> |
|
<td>67.5</td> |
|
</tr> |
|
<tr> |
|
<td>MMLU-PRO (5-shot)</td> |
|
<td>32.7</td> |
|
<td><b>43.5</b></td> |
|
<td>41.4</td> |
|
<td>39.2</td> |
|
</tr> |
|
<tr> |
|
<td>IFEval</td> |
|
<td>12.0</td> |
|
<td>33.9</td> |
|
<td>21.2</td> |
|
<td><b>34.3</b></td> |
|
</tr> |
|
<tr> |
|
<td rowspan="2">Math</td> |
|
<td>GSM8K (5-shot)</td> |
|
<td>49.4</td> |
|
<td><b>82.9</b></td> |
|
<td>69.1</td> |
|
<td>76.2</td> |
|
</tr> |
|
<tr> |
|
<td>MATH Lvl-5 (4-shot)</td> |
|
<td>4.1</td> |
|
<td>15.5</td> |
|
<td>10.5</td> |
|
<td><b>18.0</b></td> |
|
</tr> |
|
<tr> |
|
<td rowspan="4">Reasoning</td> |
|
<td>Arc Challenge (25-shot)</td> |
|
<td>58.2</td> |
|
<td>63.2</td> |
|
<td><b>67.5</b></td> |
|
<td>63.1</td> |
|
</tr> |
|
<tr> |
|
<td>GPQA (0-shot)</td> |
|
<td>31.0</td> |
|
<td>33.0</td> |
|
<td>33.4</td> |
|
<td><b>35.5</b></td> |
|
</tr> |
|
<tr> |
|
<td>MUSR (0-shot)</td> |
|
<td>38.0</td> |
|
<td>44.2</td> |
|
<td>45.3</td> |
|
<td><b>47.3</b></td> |
|
</tr> |
|
<tr> |
|
<td>BBH (3-shot)</td> |
|
<td>46.5</td> |
|
<td>54.0</td> |
|
<td><b>54.3</b></td> |
|
<td>51.0</td> |
|
</tr> |
|
<tr> |
|
<td rowspan="4">CommonSense Understanding</td> |
|
<td>PIQA (0-shot)</td> |
|
<td>81.2</td> |
|
<td>79.9</td> |
|
<td><b>82.9</b></td> |
|
<td>79.1</td> |
|
</tr> |
|
<tr> |
|
<td>SciQ (0-shot)</td> |
|
<td>94.6</td> |
|
<td>95.2</td> |
|
<td><b>97.1</b></td> |
|
<td>92.4</td> |
|
</tr> |
|
<tr> |
|
<td>Winogrande (0-shot)</td> |
|
<td>74.0</td> |
|
<td>72.9</td> |
|
<td><b>74.2</b></td> |
|
<td>71.0</td> |
|
</tr> |
|
<tr> |
|
<td>OpenbookQA (0-shot)</td> |
|
<td>44.8</td> |
|
<td>47.0</td> |
|
<td><b>47.2</b></td> |
|
<td>43.8</td> |
|
</tr> |
|
</tbody> |
|
</table> |
|
|
|
## Technical Report |
|
Coming soon.... |
|
|
|
## Citation |
|
If Falcon3 family were helpful to your work, feel free to give us a cite. |
|
|
|
``` |
|
@misc{Falcon3, |
|
title = {The Falcon 3 family of Open Models}, |
|
author = {TII Team}, |
|
month = {December}, |
|
year = {2024} |
|
} |
|
``` |
