Instructions to use flozi00/falcon-7b-german-assistant-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flozi00/falcon-7b-german-assistant-v2 with Transformers:

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

pipe = pipeline("text-generation", model="flozi00/falcon-7b-german-assistant-v2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("flozi00/falcon-7b-german-assistant-v2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use flozi00/falcon-7b-german-assistant-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flozi00/falcon-7b-german-assistant-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flozi00/falcon-7b-german-assistant-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/flozi00/falcon-7b-german-assistant-v2

SGLang

How to use flozi00/falcon-7b-german-assistant-v2 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 "flozi00/falcon-7b-german-assistant-v2" \
    --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": "flozi00/falcon-7b-german-assistant-v2",
		"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 "flozi00/falcon-7b-german-assistant-v2" \
        --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": "flozi00/falcon-7b-german-assistant-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flozi00/falcon-7b-german-assistant-v2 with Docker Model Runner:
```
docker model run hf.co/flozi00/falcon-7b-german-assistant-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This project is sponsored by

Model Card

This model is an finetuned version for german instructions and conversations in style of Open Assistant tokens. "<|prompter|>" "<|endoftext|>" "<|assistant|>"

The dataset used is deduplicated and cleaned, with no codes inside. The focus is on instruction following and conversational tasks.

The model archictecture is based on falcon with 7B parameters, trained on 100% renewable energy powered hardware.

This work is contributed by private research of flozi00

Downloads last month: 22

Safetensors

Model size

7B params

Tensor type

F16

Model tree for flozi00/falcon-7b-german-assistant-v2

Quantizations

1 model

flozi00
/

falcon-7b-german-assistant-v2

This project is sponsored by

Model Card

Model tree for flozi00/falcon-7b-german-assistant-v2

Dataset used to train flozi00/falcon-7b-german-assistant-v2