Instructions to use Jotschi/Mistral-7B-v0.1-coco-caption-de with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jotschi/Mistral-7B-v0.1-coco-caption-de with Transformers:

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

pipe = pipeline("text-generation", model="Jotschi/Mistral-7B-v0.1-coco-caption-de")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jotschi/Mistral-7B-v0.1-coco-caption-de")
model = AutoModelForCausalLM.from_pretrained("Jotschi/Mistral-7B-v0.1-coco-caption-de")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Jotschi/Mistral-7B-v0.1-coco-caption-de with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jotschi/Mistral-7B-v0.1-coco-caption-de"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jotschi/Mistral-7B-v0.1-coco-caption-de",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Jotschi/Mistral-7B-v0.1-coco-caption-de

SGLang

How to use Jotschi/Mistral-7B-v0.1-coco-caption-de 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 "Jotschi/Mistral-7B-v0.1-coco-caption-de" \
    --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": "Jotschi/Mistral-7B-v0.1-coco-caption-de",
		"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 "Jotschi/Mistral-7B-v0.1-coco-caption-de" \
        --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": "Jotschi/Mistral-7B-v0.1-coco-caption-de",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Jotschi/Mistral-7B-v0.1-coco-caption-de with Docker Model Runner:
```
docker model run hf.co/Jotschi/Mistral-7B-v0.1-coco-caption-de
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Mistral7B-v0.1-coco-caption-de

This model is a fine-tuned model of the Mistral7B-v0.1 completion model and meant to produce german COCO like captions.

The coco-karpathy-opus-de dataset was used to tune the model for german image caption generation.

Model Details

Prompt format

The completion model is trained with the prompt prefix Bildbeschreibung:

Examples:

>>> Bildbeschreibung: 
2 Hunde sitzen auf einer Bank neben einer Pflanze

>>> Bildbeschreibung: Wasser
fall und Felsen vor dem Gebäude mit Blick auf den Fluss.

>>> Bildbeschreibung: Ein grünes Auto mit roten 
 Reflektoren parkte auf dem Parkplatz.

Model Description

Developed by: Jotschi
License: Apache License
Finetuned from model: Mistral7B-v0.1

Uses

The model is meant to be used in conjunction with a BLIP2 Q-Former to enable image captioning, visual question answering (VQA) and chat-like conversations.