README.md

---
license: apache-2.0
datasets:
- tiiuae/falcon-refinedweb
pipeline_tag: text-generation
library_name: openlm
tags:
- mamba
- linear
language:
- en
model-index:
- name: mamba-7b
  results:
  - task:
      type: text-generation
    dataset:
      type: MMLU
      name: MMLU
    metrics:
    - name: accuracy
      type: accuracy
      value: 33.3
      verified: false
  - task:
      type: text-generation
    dataset:
      type: HellaSwag
      name: HellaSwag
    metrics:
    - name: accuracy
      type: accuracy
      value: 77.9
      verified: false
  - task:
      type: text-generation
    dataset:
      type: PIQA
      name: PIQA
    metrics:
    - name: accuracy
      type: accuracy
      value: 81.0
      verified: false
  - task:
      type: text-generation
    dataset:
      type: Winogrande
      name: Winogrande
    metrics:
    - name: accuracy
      type: accuracy
      value: 71.8
      verified: false
  - task:
      type: text-generation
    dataset:
      type: ai2_arc
      name: ARC-E
    metrics:
    - name: accuracy
      type: accuracy
      value: 77.5
      verified: false
  - task:
      type: text-generation
    dataset:
      type: ai2_arc
      name: ARC-C
    metrics:
    - name: accuracy
      type: accuracy
      value: 46.7
      verified: false
---

# Mamba-7B
(insert cool midjourney pic here?)<br>
This is a 7B parameter model with the [Mamba](https://arxiv.org/abs/2312.00752) architecture, trained on 1.2T tokens of the [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) dataset.
Mamba is a state-space model that does not use self-attention unlike the standard transformer architecture. It has shown strong performance on various natural language benchmarks. To date, the largest publicly released pure-Mamba pretrain is [Mamba-2.8B](https://huggingface.co/state-spaces/mamba-2.8b). 
We follow their training recipe and release our version of Mamba-7B.

## Model Details
- **Developed by**: [Toyota Research Institute](https://www.tri.global/our-work/robotics)
- **Model Type**: This is an auto-regressive language model based on the [Mamba](https://arxiv.org/abs/2312.00752) architecture.
- **Dataset**: Trained on 1.2T tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) 
- **Tokenizer**: `EleutherAI/gpt-neox-20b`
- **Library**: [OpenLM](https://github.com/mlfoundations/open_lm/)
- **License**: This model is licensed under [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0).
 
| Parameters | Hidden Size | Layers | Vocab Size | Sequence Length | 
|------------|-------------|--------| ---------- | --------------- |
| 7B         | 4096        | 64     | 50432      | 2048            |

## Training Details
- Mamba-7B was trained using AWS SageMaker on 128 H100 80GB GPUs.
- Training began in March 2024 and lasted around 3 weeks (some down time due to crashes and loss spikes)
| **Hyperparameter** | **Value**  | 
|--------------------|------------|
| Precision          | `bfloat16` |
| Optimizer          | AdamW      |
| Learning rate      | 3e-4       |
| LR cooldown end    | 1e-5       |
| QK-norm            | False      |
| Warmup steps       | 2000       |
| Z-loss             | 1e-4       |
| Batch size         | 2M         |


## Usage
This model was trained using [OpenLM](https://github.com/mlfoundations/open_lm/). The weights have been converted to be compatible with HuggingFace.

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("tri-ml/mamba-7b-rw")
model = AutoModelForCausalLM.from_pretrained("tri-ml/mamba-7b-rw").cuda()

inputs = tokenizer(["A beautiful flower"], return_tensors="pt")
gen_kwargs = {"max_length": 128, "top_p": 0.8, "temperature": 0.8, "do_sample": True, "repetition_penalty": 1.1}
output = model.generate(inputs['input_ids'], **gen_kwargs)
output = tokenizer.decode(output[0].tolist(), skip_special_tokens=True)
print(output)
# <s> A beautiful flower box made of white rose wood. It is a perfect gift for weddings, birthdays and anniversaries.
# All the roses are from our farm Roses Flanders. Therefor you know that these flowers last much longer than those in store or online!</s>
```


## Performance Evaluation
Our evaluations were done using the [Eleuther LM Eval Harness](https://github.com/EleutherAI/lm-evaluation-harness) repo.

Below we report the performance of Mamba 7B compared to other base models.

<style>
    .evalTable th { background: white; }
    .evalTable tr:nth-child(1) { background: #f3f3f3; }
    .evalTable tr:nth-child(2) { background: #f3f3f3; }
    .evalTable tr:nth-child(6) { background: #f3f3f3; }
</style>

<div class="evalTable">


|                   | HellaSwag     | PIQA     | Winogrande     | ARC-E     | ARC-C     | MMLU (5-shot)    |
| ----------------- | ------------- | -------- | -------------- | --------- | --------- | ---------------- |
| Mamba-1.4B        | 59.0          | 73.9     | 61.4           | 65.5      | 32.9      | 25.2             |
| Mamba-2.8B        | 71.0          | 78.1     | 65.9           | 68.2      | 41.7      | 26.2             |
| Llama2-7B         | 76.0          | 79.1     | 69.1           | 76.3      | 46.3      | 45.9             |
| Gemma-7B          | 80.7          | 81.9     | 73.7           | 81.1      | 53.2      | 62.9             |
| Mistral-7B        | 81.0          | 82.1     | 74.0           | 80.9      | 53.8      | 62.4             |
| **Mamba-7B**      | 77.9          | 81.0     | 71.8           | 77.5      | 46.7      | 33.3             |

</div>


## How to Cite
If you use this model, please cite our paper on Linearizing Large Language Models.
```
@article{Mercat2024Linearizing,
  title={Linearizing Large Language Models},
  author={Jean Mercat and Igor Vasiljevic and Sedrick Keh and Kushal Arora and Achal Dave and Adrien Gaidon and Thomas Kollar},
  journal={ArXiv},
  year={2024},
  volume={},
}
```

## Citations
Mamba
```
@article{mamba,
  title={Mamba: Linear-Time Sequence Modeling with Selective State Spaces},
  author={Gu, Albert and Dao, Tri},
  journal={arXiv preprint arXiv:2312.00752},
  year={2023}
}
```
OpenLM
```
@misc{open_lm,
  author = {Gururangan, Suchin and Wortsman, Mitchell and Gadre, Samir Yitzhak and Dave, Achal and Kilian, Maciej and Shi, Weijia and Mercat, Jean and Smyrnis, Georgios and Ilharco, Gabriel and Jordan, Matt and Heckel, Reinhard and Dimakis, Alex and Farhadi, Ali and Shankar, Vaishaal and Schmidt, Ludwig},
  title = {{open_lm}:  a minimal but performative language modeling (LM) repository},
  year = {2023},
  note = {GitHub repository},
  url = {https://github.com/mlfoundations/open_lm/}
}
```