Instructions to use 0labs-in/Sky-v1.3-IN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0labs-in/Sky-v1.3-IN with Transformers:

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

pipe = pipeline("text-generation", model="0labs-in/Sky-v1.3-IN", 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/Sky-v1.3-IN", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use 0labs-in/Sky-v1.3-IN with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0labs-in/Sky-v1.3-IN"
# 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/Sky-v1.3-IN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0labs-in/Sky-v1.3-IN

SGLang

How to use 0labs-in/Sky-v1.3-IN 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/Sky-v1.3-IN" \
    --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/Sky-v1.3-IN",
		"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/Sky-v1.3-IN" \
        --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/Sky-v1.3-IN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0labs-in/Sky-v1.3-IN with Docker Model Runner:
```
docker model run hf.co/0labs-in/Sky-v1.3-IN
```

Atharvsinh commited on 27 days ago

Commit

508cbd9

verified ·

1 Parent(s): c097e5b

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -7

README.md CHANGED Viewed

@@ -1,6 +1,4 @@
 ---
-license: other
-base_model: 0labs-in/V1.3-CSD
 library_name: transformers
 pipeline_tag: text-generation
 tags:
@@ -14,12 +12,10 @@ tags:
 # Sky-v1.3-IN
-Sky-v1.3-IN is an experimental full merged research checkpoint from 0labs.
-- Base model: `0labs-in/V1.3-CSD`
 - Adapter source: `0labs-in/Sky-v1.3-IN-Cobra-Adapter`
 - Method: CSD + COBRA context-boundary supervised tuning
-- Release type: merged full model weights
-- Status: experimental research candidate
-`0labs-in/V1.3-CSD` remains the protected stable public model.

 ---
 library_name: transformers
 pipeline_tag: text-generation
 tags:
 # Sky-v1.3-IN
+Sky-v1.3-IN is an research with Cognitive Scaffolding Decay & COBRA- 0labs.
 - Adapter source: `0labs-in/Sky-v1.3-IN-Cobra-Adapter`
 - Method: CSD + COBRA context-boundary supervised tuning
+- Status: final research candidate
+`0labs-in/V1.3-IN` remains the protected stable public model.