|
--- |
|
language: |
|
- en |
|
tags: |
|
- falcon3 |
|
- falcon3_mamba |
|
- falcon_mamba |
|
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/falcon_mamba/falcon-mamba-logo.png" alt="drawing" width="500"/> |
|
</div> |
|
|
|
# Falcon3-Mamba-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-Mamba-7B**. It achieves, compared to similar SSM-based models of the same size, state of art results (at release's time) on reasoning, language understanding, instruction following, code and mathematics tasks. |
|
Falcon3-Mamba-7B-Base supports a context length up to 32K and was mainly trained on english corpus. |
|
|
|
## Model Details |
|
- Architecture (same as [Falcon-Mamba-7b](https://huggingface.co/tiiuae/falcon-mamba-7b)) |
|
- Mamba1 based causal decoder only architecture trained on a causal language modeling task (i.e., predict the next token). |
|
- 64 decoder blocks |
|
- width: 4096 |
|
- state dimension: 16 |
|
- 32k context length |
|
- 65k vocab size |
|
- Continue Pretrained from Falcon Mamba 7B, with another 1500 Gigatokens of data comprising of web, code, STEM and high quality data. |
|
- Postrained on 1.2 million samples of STEM, conversations, code, and safety. |
|
- 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 |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model_name = "tiiuae/Falcon3-Mamba-7B-Base" |
|
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
model_name, |
|
torch_dtype="auto", |
|
device_map="auto" |
|
) |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
|
|
prompt = "How many hours in one day?" |
|
messages = [ |
|
{"role": "system", "content": "You are a helpful friendly assistant Falcon3 from TII, try to follow instructions as much as possible."}, |
|
{"role": "user", "content": prompt} |
|
] |
|
text = tokenizer.apply_chat_template( |
|
messages, |
|
tokenize=False, |
|
add_generation_prompt=True |
|
) |
|
model_inputs = tokenizer([text], return_tensors="pt").to(model.device) |
|
|
|
generated_ids = model.generate( |
|
**model_inputs, |
|
max_new_tokens=1024 |
|
) |
|
generated_ids = [ |
|
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) |
|
] |
|
|
|
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] |
|
print(response) |
|
``` |
|
|
|
</details> |
|
|
|
<br> |
|
|
|
# Benchmarks |
|
We report in the following table our internal pipeline benchmarks. For the benchmarks marked by star, we normalize the results with HuggingFace score normalization: |
|
|
|
<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>Zamba2-7B</th> |
|
<th>Llama-3.1-8B</th> |
|
<th>Falcon-Mamba-7B</th> |
|
<th>Falcon3-Mamba-7B-Base</th> |
|
</tr> |
|
</thead> |
|
<tbody> |
|
<tr> |
|
<td rowspan="3">General</td> |
|
<td>MMLU (5-shot)</td> |
|
<td>64.9</td> |
|
<td>66.4</td> |
|
<td>59.9</td> |
|
<td>64.9</td> |
|
</tr> |
|
<tr> |
|
<td>MMLU-PRO (5-shot)*</td> |
|
<td>24.5</td> |
|
<td>24.9</td> |
|
<td>14.5</td> |
|
<td>22.6</td> |
|
</tr> |
|
<tr> |
|
<td>IFEval</td> |
|
<td>37.4</td> |
|
<td>12.7</td> |
|
<td>33.4</td> |
|
<td>30.1</td> |
|
</tr> |
|
<tr> |
|
<td rowspan="2">Math</td> |
|
<td>GSM8K (5-shot)</td> |
|
<td>55.8</td> |
|
<td>47.9</td> |
|
<td>51.3</td> |
|
<td>65.9</td> |
|
</tr> |
|
<tr> |
|
<td>MATH (4-shot)</td> |
|
<td>10.3</td> |
|
<td>5.1</td> |
|
<td>3.6</td> |
|
<td>15.6</td> |
|
</tr> |
|
<tr> |
|
<td rowspan="4">Reasoning</td> |
|
<td>Arc Challenge (25-shot)</td> |
|
<td>54.1</td> |
|
<td>58.5</td> |
|
<td>55.9</td> |
|
<td>56.7</td> |
|
</tr> |
|
<tr> |
|
<td>GPQA (0-shot)*</td> |
|
<td>9.4</td> |
|
<td>6.2</td> |
|
<td>8.1</td> |
|
<td>10.6</td> |
|
</tr> |
|
<tr> |
|
<td>MUSR (0-shot)*</td> |
|
<td>7.5</td> |
|
<td>8.9</td> |
|
<td>10.9</td> |
|
<td>4.5</td> |
|
</tr> |
|
<tr> |
|
<td>BBH (3-shot)*</td> |
|
<td>27.9</td> |
|
<td>25.3</td> |
|
<td>19.9</td> |
|
<td>25.6</td> |
|
</tr> |
|
<tr> |
|
<td rowspan="4">CommonSense Understanding</td> |
|
<td>PIQA (0-shot)</td> |
|
<td>79.27</td> |
|
<td>81.2</td> |
|
<td>80.2</td> |
|
<td>79.54</td> |
|
</tr> |
|
<tr> |
|
<td>SciQ (0-shot)</td> |
|
<td>94.4</td> |
|
<td>94.6</td> |
|
<td>96.3</td> |
|
<td>92.0</td> |
|
</tr> |
|
<tr> |
|
<td>Winogrande (0-shot)</td> |
|
<td>77.4</td> |
|
<td>74.0</td> |
|
<td>74.9</td> |
|
<td>71.27</td> |
|
</tr> |
|
</tbody> |
|
|
|
</table> |
|
|
|
## Useful links |
|
- View our [release blogpost](https://huggingface.co/blog/falcon3). |
|
- Feel free to join [our discord server](https://discord.gg/fwXpMyGc) if you have any questions or to interact with our researchers and developers. |
|
|
|
## 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}, |
|
author = {Falcon-LLM Team}, |
|
month = {December}, |
|
year = {2024} |
|
} |
|
``` |
