Ling Lite 1.5

🚀 Ling

Ling is a Mixture-of-Experts (MoE) Large Language Model (LLM) provided and open-sourced by InclusionAI. It comes in two sizes: Ling-lite and Ling-plus. These models offer remarkable performance and scalability, suitable for a wide range of natural language processing tasks.

Paper

🤗 Hugging Face

✨ Features

Ling is a MoE LLM provided and open-sourced by InclusionAI. There are two different sizes available: Ling-lite and Ling-plus. Ling-lite has 16.8 billion parameters with 2.75 billion activated parameters, while Ling-plus has 290 billion parameters with 28.8 billion activated parameters. Compared to existing models in the industry, both models show impressive performance.

Their structure allows for easy scaling up and down and adaptation to different tasks. Therefore, users can utilize these models for a wide variety of tasks, from natural language processing to solving complex problems. Moreover, the open-source nature of Ling promotes collaboration and innovation within the AI community, enabling a diverse range of use cases and enhancements.

As more developers and researchers engage with the platform, we can anticipate rapid advancements and improvements, leading to even more sophisticated applications. This collaborative approach accelerates development and ensures that the models stay at the forefront of technology, addressing emerging challenges in various fields.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

Here is a code snippet to show you how to use the chat model with transformers:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "inclusionAI/Ling-lite-1.5"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Give me a short introduction to large language models."
messages = [
    {"role": "system", "content": "You are Ling, an assistant created by inclusionAI"},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

📚 Documentation

Model Downloads

You can refer to the following table to see the various parameters for your use case. If you are located in mainland China, we also provide the model on ModelScope.cn to speed up the download process.

Evaluation

Context Window

Evaluation results on the Needle In A Haystack (NIAH) tests. Ling-Lite-1.5 has improved long text generation capability and performs well across most context window lengths up to 128K.

Deployment

Please refer to Github

📄 License

This code repository is licensed under the MIT License.

📚 Citation

If you find our work helpful, feel free to give us a cite.

@article{ling,
    title   = {Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs}, 
    author  = {Ling Team},
    journal = {arXiv preprint arXiv:2503.05139},
    year    = {2025}
}