Instructions to use hatanp/gpt-fi-distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hatanp/gpt-fi-distill with Transformers:

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

pipe = pipeline("text-generation", model="hatanp/gpt-fi-distill")

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

tokenizer = AutoTokenizer.from_pretrained("hatanp/gpt-fi-distill")
model = AutoModelForCausalLM.from_pretrained("hatanp/gpt-fi-distill", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hatanp/gpt-fi-distill with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hatanp/gpt-fi-distill

SGLang

How to use hatanp/gpt-fi-distill 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 "hatanp/gpt-fi-distill" \
    --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": "hatanp/gpt-fi-distill",
		"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 "hatanp/gpt-fi-distill" \
        --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": "hatanp/gpt-fi-distill",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hatanp/gpt-fi-distill with Docker Model Runner:
```
docker model run hf.co/hatanp/gpt-fi-distill
```

DEPRECATED!

This model is old and no longer relevant with the releases of all around better Finnish models such as GPT-3 models from TurkuNLP

You may of course still use this for experiments and benchmarking, but I doubt this will work any better.

Old description:

Knowledge distilled version of a larger model gpt-fi. This model has approximately 300M parameters compared to the 1.2B parameters of the larger model. For scripts and more complete model information refer to the large models' page.

Downloads last month: 229