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, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

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
```

Context Size of EM German Mistral

by weissenbacherpwc - opened Nov 7, 2023

Discussion

weissenbacherpwc

Nov 7, 2023

Hi,

I am wondering what the maximum context size of the model is? Is is 2048?

jphme

Owner Nov 9, 2023

It´s trained at a max 4096 context window (next version will probably be 8k+) and the max context size of the architecture is 32k token, see details here: https://huggingface.co/jphme/em_german_mistral_v01/blob/main/config.json . You should be able to scale the context window up to at least 8k using rope scaling (see here: https://huggingface.co/docs/transformers/main/en/model_doc/llama#transformers.LlamaConfig.rope_scaling ).

jphme changed discussion status to closed Nov 9, 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