Instructions to use Kwaipilot/KwaiCoder-DS-V2-Lite-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kwaipilot/KwaiCoder-DS-V2-Lite-Base with Transformers:

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

pipe = pipeline("text-generation", model="Kwaipilot/KwaiCoder-DS-V2-Lite-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kwaipilot/KwaiCoder-DS-V2-Lite-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Kwaipilot/KwaiCoder-DS-V2-Lite-Base", trust_remote_code=True)
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kwaipilot/KwaiCoder-DS-V2-Lite-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kwaipilot/KwaiCoder-DS-V2-Lite-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kwaipilot/KwaiCoder-DS-V2-Lite-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kwaipilot/KwaiCoder-DS-V2-Lite-Base

SGLang

How to use Kwaipilot/KwaiCoder-DS-V2-Lite-Base 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 "Kwaipilot/KwaiCoder-DS-V2-Lite-Base" \
    --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": "Kwaipilot/KwaiCoder-DS-V2-Lite-Base",
		"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 "Kwaipilot/KwaiCoder-DS-V2-Lite-Base" \
        --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": "Kwaipilot/KwaiCoder-DS-V2-Lite-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kwaipilot/KwaiCoder-DS-V2-Lite-Base with Docker Model Runner:
```
docker model run hf.co/Kwaipilot/KwaiCoder-DS-V2-Lite-Base
```

KwaiCoder-DS-V2-Lite-Base

Commit History

Adding `safetensors` variant of this model

6e08037
verified

SFconvertbot commited on Jan 2, 2025

Update README.md

60cbb00
verified

binglinchengxia commited on Jan 2, 2025

Update README.md

b0b7604
verified

binglinchengxia commited on Jan 2, 2025

Update README.md

ed0dffb
verified

binglinchengxia commited on Jan 2, 2025

Update README.md

5808a41
verified

binglinchengxia commited on Jan 2, 2025

Update README.md

9c0a011
verified

binglinchengxia commited on Dec 31, 2024

Update README.md

463ffae
verified

binglinchengxia commited on Dec 31, 2024

Update README.md

f0dafd6
verified

binglinchengxia commited on Dec 31, 2024

Update README.md

0787f38
verified

binglinchengxia commited on Dec 31, 2024

Update README.md

f71df81
verified

binglinchengxia commited on Dec 31, 2024

Create README.md

269fb2e
verified

binglinchengxia commited on Dec 31, 2024

init

0fc9ed5

root commited on Dec 2, 2024

initial commit

ce4d41d
verified

zhangxiaojiang commited on Dec 2, 2024

Commit History

Adding `safetensors` variant of this model 6e08037 verified

Update README.md 60cbb00 verified

Update README.md b0b7604 verified

Update README.md ed0dffb verified

Update README.md 5808a41 verified

Update README.md 9c0a011 verified

Update README.md 463ffae verified

Update README.md f0dafd6 verified

Update README.md 0787f38 verified

Update README.md f71df81 verified

Create README.md 269fb2e verified

init 0fc9ed5

initial commit ce4d41d verified

Adding `safetensors` variant of this model

6e08037
verified

Update README.md

60cbb00
verified

Update README.md

b0b7604
verified

Update README.md

ed0dffb
verified

Update README.md

5808a41
verified

Update README.md

9c0a011
verified

Update README.md

463ffae
verified

Update README.md

f0dafd6
verified

Update README.md

0787f38
verified

Update README.md

f71df81
verified

Create README.md

269fb2e
verified

init

0fc9ed5

initial commit

ce4d41d
verified