Instructions to use jphme/em_german_mistral_v01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jphme/em_german_mistral_v01 with Transformers:

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

pipe = pipeline("text-generation", model="jphme/em_german_mistral_v01")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("jphme/em_german_mistral_v01")
model = AutoModelForMultimodalLM.from_pretrained("jphme/em_german_mistral_v01")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jphme/em_german_mistral_v01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jphme/em_german_mistral_v01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jphme/em_german_mistral_v01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jphme/em_german_mistral_v01

SGLang

How to use jphme/em_german_mistral_v01 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 "jphme/em_german_mistral_v01" \
    --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": "jphme/em_german_mistral_v01",
		"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 "jphme/em_german_mistral_v01" \
        --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": "jphme/em_german_mistral_v01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jphme/em_german_mistral_v01 with Docker Model Runner:
```
docker model run hf.co/jphme/em_german_mistral_v01
```

Upload .bin files

by windprak - opened Oct 12, 2023

Discussion

windprak

Oct 12, 2023

Could you upload .bin files? Safetensors don't work in some frameworks.

jphme

Owner Oct 12, 2023

Could you upload .bin files? Safetensors don't work in some frameworks.

Happy to help, but could you provide me details about your usecase and the framework that doesn't support safetensors? Its no possible to upgrade to a new version? And which model versions are of interest for you?

I don't like to upload both versions and just switched to safetensors for EM German because I never heard of any problems. If there is sufficient demand I'm happy to provide .bin as well...

windprak

Oct 12, 2023

•

edited Oct 12, 2023

https://github.com/Lightning-AI/lit-gpt/issues/450
Thanks I think I have an answer now.

jphme

Owner Oct 12, 2023

Perfect!
If there are any problems let me know - as lit gpt is probably only used by technical people that are able to covert themselves I would prefer staying with just one format, as creating/uploading 2 formats creates a lot of overhead and traffic. But should there be more demand I would surely be able to provide bin as well for the most popular models.

jphme changed discussion status to closed Oct 12, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment