Instructions to use 0labs-in/V1.3-CSD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0labs-in/V1.3-CSD with Transformers:

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

pipe = pipeline("text-generation", model="0labs-in/V1.3-CSD", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("0labs-in/V1.3-CSD", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use 0labs-in/V1.3-CSD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0labs-in/V1.3-CSD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0labs-in/V1.3-CSD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0labs-in/V1.3-CSD

SGLang

How to use 0labs-in/V1.3-CSD 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 "0labs-in/V1.3-CSD" \
    --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": "0labs-in/V1.3-CSD",
		"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 "0labs-in/V1.3-CSD" \
        --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": "0labs-in/V1.3-CSD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0labs-in/V1.3-CSD with Docker Model Runner:
```
docker model run hf.co/0labs-in/V1.3-CSD
```

V1.3-CSD / csd_smoke_eval.json

Atharvsinh

Upload Sky v1.3 CSD checkpoint

7b713b4 verified 26 days ago

raw

history blame contribute delete

1.41 kB

	[
	{
	"prompt": "hello",
	"answer": "Hello. How can I help?"
	},
	{
	"prompt": "who are you?",
	"answer": "I am Sky v1.3, an AI assistant developed by 0labs and created by Atharvsinh Jadav. I help with coding, debugging, reasoning, and general questions."
	},
	{
	"prompt": "are you Phi-4?",
	"answer": "No. I am Sky v1.3 from 0labs."
	},
	{
	"prompt": "what is AI?",
	"answer": "AI, or artificial intelligence, is software designed to perform tasks that normally require human intelligence, such as understanding language, recognizing patterns, making predictions, solving problems, or generating content."
	},
	{
	"prompt": "write a Python function to check if a string is a palindrome",
	"answer": "```python\ndef is_palindrome(s):\n s = ''.join(c.lower() for c in s if c.isalnum())\n return s == s[::-1]\n```\nThis removes non-alphanumeric characters, converts to lowercase, and checks the reversed string."
	},
	{
	"prompt": "Explain async await in simple words.",
	"answer": "`async` makes a function that can pause and wait for work to finish without blocking everything else. `await` is used inside it to say \"wait here until this task finishes\" before moving on."
	},
	{
	"prompt": "Return only JSON with keys name, version, creator for Sky v1.3.",
	"answer": "{\"name\":\"Sky\",\"version\":\"v1.3\",\"creator\":\"Atharvsinh Jadav\"}"
	}
	]