Instructions to use NovaSky-AI/Sky-T1-32B-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NovaSky-AI/Sky-T1-32B-Flash with Transformers:

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

pipe = pipeline("text-generation", model="NovaSky-AI/Sky-T1-32B-Flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NovaSky-AI/Sky-T1-32B-Flash")
model = AutoModelForCausalLM.from_pretrained("NovaSky-AI/Sky-T1-32B-Flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NovaSky-AI/Sky-T1-32B-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NovaSky-AI/Sky-T1-32B-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NovaSky-AI/Sky-T1-32B-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NovaSky-AI/Sky-T1-32B-Flash

SGLang

How to use NovaSky-AI/Sky-T1-32B-Flash 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 "NovaSky-AI/Sky-T1-32B-Flash" \
    --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": "NovaSky-AI/Sky-T1-32B-Flash",
		"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 "NovaSky-AI/Sky-T1-32B-Flash" \
        --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": "NovaSky-AI/Sky-T1-32B-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NovaSky-AI/Sky-T1-32B-Flash with Docker Model Runner:
```
docker model run hf.co/NovaSky-AI/Sky-T1-32B-Flash
```

Improve model card: Add paper URL, pipeline tag and Github URL

by nielsr HF Staff - opened Feb 16, 2025

base: refs/heads/main

←

from: refs/pr/6

Discussion Files changed

-5

Files changed (1) hide show

README.md +9 -5

README.md CHANGED Viewed

@@ -1,14 +1,15 @@
 ---
-library_name: transformers
 datasets:
 - BAAI/TACO
 - tasksource/PRM800K
 language:
 - en
-base_model:
-- Qwen/Qwen2.5-32B-Instruct
-- NovaSky-AI/Sky-T1-32B-Preview
 license: apache-2.0
 ---
 ## Model Details
@@ -18,9 +19,11 @@ license: apache-2.0
 <!-- Provide a longer summary of what this model is. -->
 This is a 32B reasoning model preference optimized on top of Sky-T1-32B-Preview to significantly reduce generation lengths while maintaining accuracy. The performance is on par with o1-preview model in both math and coding, while reducing generation lengths by up to 57% relative to Sky-T1-32B-Preview.
-Please see our [blog post](https://novasky-ai.github.io/posts/reduce-overthinking/) for more details.
 - **Developed by:** NovaSky Team from Sky Computing Lab at UC Berkeley.
 ## Training Details
@@ -71,3 +74,4 @@ Please considering citing our blog post if you found it useful for your research
   note         = {Accessed: 2025-01-23},
   year         = {2025}
 }

 ---
+base_model:
+- Qwen/Qwen2.5-32B-Instruct
+- NovaSky-AI/Sky-T1-32B-Preview
 datasets:
 - BAAI/TACO
 - tasksource/PRM800K
 language:
 - en
+library_name: transformers
 license: apache-2.0
+pipeline_tag: text-generation
 ---
 ## Model Details
 <!-- Provide a longer summary of what this model is. -->
 This is a 32B reasoning model preference optimized on top of Sky-T1-32B-Preview to significantly reduce generation lengths while maintaining accuracy. The performance is on par with o1-preview model in both math and coding, while reducing generation lengths by up to 57% relative to Sky-T1-32B-Preview.
+Please see our [blog post](https://novasky-ai.github.io/posts/reduce-overthinking/) and [Sky-T1 blog post](https://novasky-ai.github.io/posts/sky-t1/) for more details.
 - **Developed by:** NovaSky Team from Sky Computing Lab at UC Berkeley.
+- **Paper:** [LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!](https://hf.co/papers/2502.07374)
+- **Code:** [https://github.com/NovaSky-AI/SkyThought](https://github.com/NovaSky-AI/SkyThought)
 ## Training Details
   note         = {Accessed: 2025-01-23},
   year         = {2025}
 }
+```