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

Libraries

How to use mhenrichsen/hestenettetLM with Transformers:

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

pipe = pipeline("text-generation", model="mhenrichsen/hestenettetLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mhenrichsen/hestenettetLM")
model = AutoModelForCausalLM.from_pretrained("mhenrichsen/hestenettetLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mhenrichsen/hestenettetLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mhenrichsen/hestenettetLM

SGLang

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

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

hestenettetLM / README.md

mhenrichsen

Update README.md

22df361 almost 3 years ago

preview code

Raw

History Blame Contribute Delete

808 Bytes

metadata

license: mit
datasets:
  - mhenrichsen/hestenettet
language:
  - da

HestenettetLM

En dansk LLM trænet på hele hestenettet over 3 epoker.

Modellen er baseret på Mistral 7b, og har et kontekstvindue på 8k.

from transformers import AutoTokenizer, TextStreamer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("mhenrichsen/hestenettetLM")
tokenizer = AutoTokenizer.from_pretrained("mhenrichsen/hestenettetLM")
streamer = TextStreamer(tokenizer, skip_special_tokens=True)


tokens = tokenizer(
    "Den bedste hest er en ", 
    return_tensors='pt'
)['input_ids']

# Generate output
generation_output = model.generate(
    tokens,
    streamer=streamer,
    max_length = 8194,
)

Eksempel: "Den bedste hest er en " bliver til: "Den bedste hest er en veltrænet hest."