Instructions to use Multi-Domain-Expert-Learning/draco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Multi-Domain-Expert-Learning/draco with Transformers:

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

pipe = pipeline("text-generation", model="Multi-Domain-Expert-Learning/draco")

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

tokenizer = AutoTokenizer.from_pretrained("Multi-Domain-Expert-Learning/draco")
model = AutoModelForCausalLM.from_pretrained("Multi-Domain-Expert-Learning/draco", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Multi-Domain-Expert-Learning/draco with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Multi-Domain-Expert-Learning/draco

SGLang

How to use Multi-Domain-Expert-Learning/draco 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 "Multi-Domain-Expert-Learning/draco" \
    --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": "Multi-Domain-Expert-Learning/draco",
		"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 "Multi-Domain-Expert-Learning/draco" \
        --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": "Multi-Domain-Expert-Learning/draco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Multi-Domain-Expert-Learning/draco with Docker Model Runner:
```
docker model run hf.co/Multi-Domain-Expert-Learning/draco
```

draco

Commit History

Sep 29, 2025

21:33
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
1cb2567

Jul 4, 2023

19:45
Upload tokenizer

Ontocord.AI

56fa503
19:45
Upload GPTBigCodeForCausalLM

Ontocord.AI

2dc836c
19:07
Upload tokenizer

Ontocord.AI

33bce14
19:07
Upload GPTBigCodeForCausalLM

Ontocord.AI

760478d
02:05
Upload tokenizer

Ontocord.AI

3814c2f
02:05
Upload GPTBigCodeForCausalLM

Ontocord.AI

e710939

Jul 3, 2023

18:22
Upload tokenizer

Ontocord.AI

fd6cf0b
18:22
Upload GPTBigCodeForCausalLM

Ontocord.AI

4ff5d07
18:01
initial commit

huu-ontocord

99e3975

Commit History

Sep 29, 2025

Adding `safetensors` variant of this model⁠

Jul 4, 2023

Upload tokenizer

Upload GPTBigCodeForCausalLM

Upload tokenizer

Upload GPTBigCodeForCausalLM

Upload tokenizer

Upload GPTBigCodeForCausalLM

Jul 3, 2023

Upload tokenizer

Upload GPTBigCodeForCausalLM

initial commit