Instructions to use inclusionAI/Ling-Coder-lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ling-Coder-lite with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ling-Coder-lite", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ling-Coder-lite", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use inclusionAI/Ling-Coder-lite with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/inclusionAI/Ling-Coder-lite

SGLang

How to use inclusionAI/Ling-Coder-lite 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 "inclusionAI/Ling-Coder-lite" \
    --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": "inclusionAI/Ling-Coder-lite",
		"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 "inclusionAI/Ling-Coder-lite" \
        --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": "inclusionAI/Ling-Coder-lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/Ling-Coder-lite with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ling-Coder-lite
```

Add link to paper and mention Github repository

by nielsr HF Staff - opened Mar 25, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-5

Files changed (1) hide show

README.md +8 -5

README.md CHANGED Viewed

@@ -1,5 +1,6 @@
 ---
-license: mit
 datasets:
 - inclusionAI/Ling-Coder-SFT
 - inclusionAI/Ling-Coder-SyntheticQA
@@ -7,14 +8,14 @@ datasets:
 language:
 - en
 - zh
-base_model:
-- inclusionAI/Ling-Coder-lite-base
-pipeline_tag: text-generation
 library_name: transformers
 tags:
 - code
 - moe
 ---
 # Ling-Coder-lite
 <p align="center">
@@ -29,6 +30,8 @@ tags:
 ## Introduction
 Ling-Coder-Lite is a MoE LLM provided and open-sourced by InclusionAI, which has 16.8 billion parameters with 2.75 billion activated parameters. Ling-Coder-Lite performs impressively on coding tasks compared to existing models in the industry. Specifically, Ling-Coder-Lite further pre-training from an intermediate checkpoint of Ling-Lite, incorporating an additional 3 trillion tokens. This extended pre-training significantly boosts the coding abilities of Ling-Lite, while preserving its strong performance in general language tasks.
 ## Model Downloads
@@ -109,4 +112,4 @@ This code repository is licensed under [the MIT License](https://huggingface.co/
       primaryClass={cs.LG},
       url={https://arxiv.org/abs/2503.17793},
 }
-```

 ---
+base_model:
+- inclusionAI/Ling-Coder-lite-base
 datasets:
 - inclusionAI/Ling-Coder-SFT
 - inclusionAI/Ling-Coder-SyntheticQA
 language:
 - en
 - zh
 library_name: transformers
+license: mit
+pipeline_tag: text-generation
 tags:
 - code
 - moe
 ---
 # Ling-Coder-lite
 <p align="center">
 ## Introduction
+This repository contains the model described in the paper [Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM](https://huggingface.co/papers/2503.17793).
 Ling-Coder-Lite is a MoE LLM provided and open-sourced by InclusionAI, which has 16.8 billion parameters with 2.75 billion activated parameters. Ling-Coder-Lite performs impressively on coding tasks compared to existing models in the industry. Specifically, Ling-Coder-Lite further pre-training from an intermediate checkpoint of Ling-Lite, incorporating an additional 3 trillion tokens. This extended pre-training significantly boosts the coding abilities of Ling-Lite, while preserving its strong performance in general language tasks.
 ## Model Downloads
       primaryClass={cs.LG},
       url={https://arxiv.org/abs/2503.17793},
 }
+```