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_training_metrics.json

Atharvsinh

Upload Sky v1.3 CSD checkpoint

7b713b4 verified 26 days ago

raw

history blame contribute delete

1.28 kB

	{
	"base_model": "sky_v1_3_5_5b_sky_runtime",
	"curriculum_dir": "csd-dataset",
	"final_dir": "sky_v1_3_csd_final",
	"total_minutes": 11.612064441045126,
	"stages": [
	{
	"train_runtime": 330.6326,
	"train_samples_per_second": 2.767,
	"train_steps_per_second": 0.172,
	"train_loss": 1.0252654144638462,
	"epoch": 0.9967213114754099,
	"stage": "stage1_scaffold",
	"minutes": 5.513923645019531,
	"train_rows": 915,
	"val_rows": 58,
	"learning_rate": 5e-07,
	"epochs": 1.0
	},
	{
	"train_runtime": 205.8567,
	"train_samples_per_second": 5.446,
	"train_steps_per_second": 0.34,
	"train_loss": 1.0430820686476572,
	"epoch": 0.9991079393398751,
	"stage": "stage2_bridge",
	"minutes": 3.435288441181183,
	"train_rows": 1121,
	"val_rows": 71,
	"learning_rate": 5e-07,
	"epochs": 1.0
	},
	{
	"train_runtime": 116.6573,
	"train_samples_per_second": 5.803,
	"train_steps_per_second": 0.36,
	"train_loss": 0.8398375312487284,
	"epoch": 0.9926144756277696,
	"stage": "stage3_clean",
	"minutes": 1.9487456480662029,
	"train_rows": 677,
	"val_rows": 43,
	"learning_rate": 4e-07,
	"epochs": 1.0
	}
	]
	}