Instructions to use omar81939/Ouro-1.4B-Thinking-depth-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use omar81939/Ouro-1.4B-Thinking-depth-SFT with Transformers:

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

pipe = pipeline("text-generation", model="omar81939/Ouro-1.4B-Thinking-depth-SFT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("omar81939/Ouro-1.4B-Thinking-depth-SFT", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use omar81939/Ouro-1.4B-Thinking-depth-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "omar81939/Ouro-1.4B-Thinking-depth-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "omar81939/Ouro-1.4B-Thinking-depth-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/omar81939/Ouro-1.4B-Thinking-depth-SFT

SGLang

How to use omar81939/Ouro-1.4B-Thinking-depth-SFT 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 "omar81939/Ouro-1.4B-Thinking-depth-SFT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "omar81939/Ouro-1.4B-Thinking-depth-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "omar81939/Ouro-1.4B-Thinking-depth-SFT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "omar81939/Ouro-1.4B-Thinking-depth-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use omar81939/Ouro-1.4B-Thinking-depth-SFT with Docker Model Runner:
```
docker model run hf.co/omar81939/Ouro-1.4B-Thinking-depth-SFT
```

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

REPO = "omar81939/Ouro-1.4B-Thinking-depth-SFT"
DEPTH = 16

tokenizer = AutoTokenizer.from_pretrained(REPO)
model = AutoModelForCausalLM.from_pretrained(
    REPO,
    trust_remote_code=True,
    dtype="bfloat16",
    total_ut_steps=DEPTH,
)

With vLLM, set hf_overrides={"total_ut_steps": DEPTH} when creating the engine.