|
--- |
|
datasets: |
|
- oscar-corpus/OSCAR-2301 |
|
- wikipedia |
|
- bjoernp/tagesschau-2018-2023 |
|
language: |
|
- en |
|
- de |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
license: apache-2.0 |
|
--- |
|
# LAION LeoLM: **L**inguistically **E**nhanced **O**pen **L**anguage **M**odel |
|
Meet LeoLM-Mistral, the first open and commercially available German Foundation Language Model built on Mistral 7b. |
|
Our models extend Llama-2's capabilities into German through continued pretraining on a large corpus of German-language and mostly locality specific text. |
|
Thanks to a compute grant at HessianAI's new supercomputer **42**, we release three foundation models trained with 8k context length. |
|
[`LeoLM/leo-mistral-hessianai-7b`](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b) under Apache 2.0 and |
|
[`LeoLM/leo-hessianai-7b`](https://huggingface.co/LeoLM/leo-hessianai-7b) and [`LeoLM/leo-hessianai-13b`](https://huggingface.co/LeoLM/leo-hessianai-13b) under the [Llama-2 community license](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt) (70b also coming soon! 👀). |
|
With this release, we hope to bring a new wave of opportunities to German open-source and commercial LLM research and accelerate adoption. |
|
Read our [blog post](https://laion.ai/blog/leo-lm/) or our paper (preprint coming soon) for more details! |
|
|
|
*A project by Björn Plüster and Christoph Schuhmann in collaboration with LAION and HessianAI.* |
|
|
|
|
|
## Model Details |
|
- **Finetuned from:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) |
|
- **Model type:** Causal decoder-only transformer language model |
|
- **Language:** English and German |
|
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.html) |
|
- **Contact:** [LAION Discord](https://discord.com/invite/eq3cAMZtCC) or [Björn Plüster](mailto:bjoern.pl@outlook.de) |
|
|
|
|
|
## Use in 🤗Transformers |
|
First install direct dependencies: |
|
``` |
|
pip install transformers torch accelerate |
|
``` |
|
If you want faster inference using flash-attention2, you need to install these dependencies: |
|
```bash |
|
pip install packaging ninja |
|
pip install flash-attn |
|
``` |
|
Then load the model in transformers: |
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
import torch |
|
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
model="LeoLM/leo-mistral-hessianai-7b", |
|
device_map="auto", |
|
torch_dtype=torch.bfloat16, |
|
use_flash_attn_2=True # optional |
|
) |
|
``` |
|
|
|
## Training parameters |
|
Note that for Mistral training, we changed learning rate to `1e-5` going down to `1e-6`. We also used Zero stage 3 and bfloat16 dtype. |
|
 |
|
|
|
|
|
## Benchmarks |
|
 |
