Instructions to use inclusionAI/Ling-flash-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ling-flash-2.0 with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ling-flash-2.0", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ling-flash-2.0", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inclusionAI/Ling-flash-2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/Ling-flash-2.0"
# 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-flash-2.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/Ling-flash-2.0

SGLang

How to use inclusionAI/Ling-flash-2.0 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-flash-2.0" \
    --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-flash-2.0",
		"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-flash-2.0" \
        --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-flash-2.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/Ling-flash-2.0 with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ling-flash-2.0
```

mx1 commited on Sep 17, 2025

Commit

5206936

verified ·

1 Parent(s): 032e97b

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -47,8 +47,8 @@ Compared with __dense models under 40B__ (e.g., Qwen3-32B-Non-Thinking, Seed-OSS
 Guided by [Ling Scaling Laws](https://arxiv.org/abs/2507.17702), Ling 2.0 adopts a __1/32 activation-ratio MoE architecture__, optimized across multiple design choices: expert granularity, shared-expert ratio, attention balance, __aux-loss-free + sigmoid routing strategy__, MTP layers, QK-Norm, Partial-RoPE, and more. These refinements enable __small-activation MoE__ models to achieve __7× efficiency gains__ over equivalent dense architectures.
 In other words, with just __6.1B activated parameters (4.8B non-embedding)__, __Ling-flash-2.0__ can match the performance of ~40B dense models. Thanks to its small activation size, it also delivers major inference speed advantages:
-● On __H20 hardware__, Ling-flash-2.0 achieves __200+ tokens/s__, offering __3× speedups__ compared to 36B dense models in everyday use.
-● With __YaRN extrapolation__, it supports __128K context length__, and as output length grows, its relative speedup can reach __7× or more__.
 <p align="center">

 Guided by [Ling Scaling Laws](https://arxiv.org/abs/2507.17702), Ling 2.0 adopts a __1/32 activation-ratio MoE architecture__, optimized across multiple design choices: expert granularity, shared-expert ratio, attention balance, __aux-loss-free + sigmoid routing strategy__, MTP layers, QK-Norm, Partial-RoPE, and more. These refinements enable __small-activation MoE__ models to achieve __7× efficiency gains__ over equivalent dense architectures.
 In other words, with just __6.1B activated parameters (4.8B non-embedding)__, __Ling-flash-2.0__ can match the performance of ~40B dense models. Thanks to its small activation size, it also delivers major inference speed advantages:
+* On __H20 hardware__, Ling-flash-2.0 achieves __200+ tokens/s__, offering __3× speedups__ compared to 36B dense models in everyday use.
+* With __YaRN extrapolation__, it supports __128K context length__, and as output length grows, its relative speedup can reach __7× or more__.
 <p align="center">