Instructions to use konstantindobler/mistral7b-de-pure-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use konstantindobler/mistral7b-de-pure-bf16 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="konstantindobler/mistral7b-de-pure-bf16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("konstantindobler/mistral7b-de-pure-bf16")
model = AutoModelForCausalLM.from_pretrained("konstantindobler/mistral7b-de-pure-bf16")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use konstantindobler/mistral7b-de-pure-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "konstantindobler/mistral7b-de-pure-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "konstantindobler/mistral7b-de-pure-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/konstantindobler/mistral7b-de-pure-bf16

SGLang

How to use konstantindobler/mistral7b-de-pure-bf16 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "konstantindobler/mistral7b-de-pure-bf16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "konstantindobler/mistral7b-de-pure-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "konstantindobler/mistral7b-de-pure-bf16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "konstantindobler/mistral7b-de-pure-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use konstantindobler/mistral7b-de-pure-bf16 with Docker Model Runner:
```
docker model run hf.co/konstantindobler/mistral7b-de-pure-bf16
```

mistral7b-de-pure-bf16

Mistral-7B-v0.1 adapted to German as part of our study on efficient language adaptation: "Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough".

Code: https://github.com/konstantinjdobler/tight-budget-llm-adaptation

Paper: https://openreview.net/forum?id=VYfJaHeVod

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("konstantindobler/mistral7b-de-pure-bf16")
model = AutoModelForCausalLM.from_pretrained("konstantindobler/mistral7b-de-pure-bf16")

# Use model and tokenizer as usual

Details

The model is based on Mistral-7B-v0.1 and was adapted to German. The original tokenizer was kept. The model was then trained on 8 billion German tokens from oscar-corpus/OSCAR-2301 with pure bfloat16 precision (no mixed precision). More details and hyperparameters can be found in the paper.

Disclaimer

The web-scale dataset used for pretraining and tokenizer training (oscar-corpus/OSCAR-2301) might contain personal and sensitive information. Such behavior needs to be assessed carefully before any real-world deployment of the models.

Citation

Please cite as follows:

@inproceedings{dobler2024language,
    title={Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough},
    author={Konstantin Dobler and Gerard de Melo},
    booktitle={2nd Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ICML 2024)},
    year={2024},
    url={https://openreview.net/forum?id=VYfJaHeVod}
}

Acknowledgements

The project on which this model is based was funded by the Federal Ministry of Education and Research under the funding code "KI-Servicezentrum Berlin-Brandenburg" 01IS22092. Responsibility for the content of this publication remains with the author.

Downloads last month: 3

Safetensors

Model size

7B params

Tensor type

BF16

konstantindobler
/

mistral7b-de-pure-bf16