---
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
---

# 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>
        <tr>
            <td>OpenbookQA (0-shot)</td>
            <td>44.8</td>
            <td>-</td>
            <td>-</td>
            <td>-</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}
}
```