Instructions to use MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B with Transformers:

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

pipe = pipeline("text-generation", model="MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B")
model = AutoModelForCausalLM.from_pretrained("MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B

SGLang

How to use MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B 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 "MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B" \
    --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": "MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B",
		"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 "MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B" \
        --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": "MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B with Docker Model Runner:
```
docker model run hf.co/MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B
```

VerwaltungsAnthologie_clear_7B

This model is used as an intermediate model for future merges. It is a merge of 4 pre-trained language models based upon Mistral-7B-v0.1 created using mergekit.

In combination with DiscoLM_German_7b_v1 this 'clear'-model is the 'base' model to build the successor of my first 'VA_talky_7B', 'VA_Disco_7B': VerwaltungsAnthologie_Disco_7B

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using mistralai/Mistral-7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

Explanations of used models

Main focus of this "clear" model is the hiig-piai/simba-v01c by the Humboldt Institute for Internet and Society has built this model for "simplified language" (Leichte Sprache in german).
The DRXD1000/Phoenix got finetuned with many german texts of law – it can even "hallucinate" almost perfect URL of the official archive of german laws: [Gesetze im Internet]](https://www.gesetze-im-internet.de/)
OpenPipe/mistral-ft-optimized-1227 performed best using mixed languages in combination with mistralai/Mistral-7B-v0.1 as base model.
VAGOsolutions/SauerkrautLM-7b-LaserChat has a wider range of colloquial german language.
mistralai/Mistral-7B-v0.1 is the base model – funny but true – only using OpenPipe/mistral-ft-optimized-1227 as base model is not as good as combining both.

Configuration

The following YAML configuration was used to produce this model:

# works but never stops
models:
  - model: mistralai/Mistral-7B-v0.1
    # No parameters necessary for base model
  - model: VAGOsolutions/SauerkrautLM-7b-LaserChat
    parameters:
      density: 0.53
      weight: 0.15
  - model: hiig-piai/simba-v01c
    parameters:
      density: 0.53
      weight: 0.55
  - model: DRXD1000/Phoenix
    parameters:
      density: 0.53
      weight: 0.15
  - model: OpenPipe/mistral-ft-optimized-1227
    parameters:
      density: 0.53
      weight: 0.15
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16
name: VerwaltungsAnthologie_clear_7B