Instructions to use danish-foundation-models/munin-7b-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use danish-foundation-models/munin-7b-alpha with Transformers:

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

pipe = pipeline("text-generation", model="danish-foundation-models/munin-7b-alpha")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("danish-foundation-models/munin-7b-alpha")
model = AutoModelForCausalLM.from_pretrained("danish-foundation-models/munin-7b-alpha", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use danish-foundation-models/munin-7b-alpha with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/danish-foundation-models/munin-7b-alpha

SGLang

How to use danish-foundation-models/munin-7b-alpha 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 "danish-foundation-models/munin-7b-alpha" \
    --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": "danish-foundation-models/munin-7b-alpha",
		"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 "danish-foundation-models/munin-7b-alpha" \
        --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": "danish-foundation-models/munin-7b-alpha",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use danish-foundation-models/munin-7b-alpha with Docker Model Runner:
```
docker model run hf.co/danish-foundation-models/munin-7b-alpha
```

Training process? Scripts?

by RASMUS - opened Jan 15, 2024

Discussion

RASMUS

Jan 15, 2024

Are you going to share training process and related scripts.
You say you use continued pretraining on LUMI but what kind of scripts you used etc.

synquid

Danish Foundation Models org Jan 15, 2024

Training scripts and many other things can be found in our Git repo: https://github.com/centre-for-humanities-computing/danish-foundation-models
Some documentation is probably outdated, but the code we've used so far just got merged in.

saattrupdan changed discussion status to closed Jan 24, 2024

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