Instructions to use Blizado/discolm-mfto-7b-german-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Blizado/discolm-mfto-7b-german-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Blizado/discolm-mfto-7b-german-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Blizado/discolm-mfto-7b-german-v0.1")
model = AutoModelForMultimodalLM.from_pretrained("Blizado/discolm-mfto-7b-german-v0.1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Blizado/discolm-mfto-7b-german-v0.1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Blizado/discolm-mfto-7b-german-v0.1

SGLang

How to use Blizado/discolm-mfto-7b-german-v0.1 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 "Blizado/discolm-mfto-7b-german-v0.1" \
    --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": "Blizado/discolm-mfto-7b-german-v0.1",
		"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 "Blizado/discolm-mfto-7b-german-v0.1" \
        --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": "Blizado/discolm-mfto-7b-german-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Blizado/discolm-mfto-7b-german-v0.1 with Docker Model Runner:
```
docker model run hf.co/Blizado/discolm-mfto-7b-german-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

This is a experimental merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Why this two models?

Because both used models are, to my knowledge, the two best models when it comes to German language generation.

DiscoLM German 7B is is up to this date (01/21/2024) by far the best German model and makes far fewer grammatical errors and his German generally sounds good. But it is finetuned on Mistral V0.2 or even V0.1.

Mistral FT Optimized 1227 is much better in German than Mistral 7B V0.2 and other German fine-tuning models that make grammar errors in almost every sentence. But even that model is a good step behind DiscoLM German 7B and creates not so well formed German sentences.

The ulterior motive was now combining this two models to get a even better German model, especially for German roleplay.

Configuration

The following YAML configuration was used to produce this model:


slices:
  - sources:
      - model: OpenPipe/mistral-ft-optimized-1227
        layer_range: [0, 32]
      - model: DiscoResearch/DiscoLM_German_7b_v1
        layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1227
parameters:
  t:
    - value: [0.5, 0.9]
dtype: bfloat16

This settings are from the model oshizo/japanese-e5-mistral-7b_slerp.

Downloads last month: 9

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Blizado/discolm-mfto-7b-german-v0.1

Merges

1 model

Quantizations