Instructions to use inclusionAI/Ling-2.6-flash-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ling-2.6-flash-base with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ling-2.6-flash-base", 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-2.6-flash-base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inclusionAI/Ling-2.6-flash-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/Ling-2.6-flash-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": "inclusionAI/Ling-2.6-flash-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/Ling-2.6-flash-base

SGLang

How to use inclusionAI/Ling-2.6-flash-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 "inclusionAI/Ling-2.6-flash-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": "inclusionAI/Ling-2.6-flash-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 "inclusionAI/Ling-2.6-flash-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": "inclusionAI/Ling-2.6-flash-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/Ling-2.6-flash-base with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ling-2.6-flash-base
```

Add transformers library tag and link to GitHub repository

by nielsr HF Staff - opened 15 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -1,12 +1,13 @@
 ---
 license: mit
 pipeline_tag: text-generation
 ---
 <p align="center">
     <img src="https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*4QxcQrBlTiAAAAAAQXAAAAgAemJ7AQ/original" width="100"/>
 </p>
-<p align="center">🤗 <a href="https://huggingface.co/inclusionAI">Hugging Face</a>&nbsp;&nbsp; | &nbsp;&nbsp;🤖 <a href="https://modelscope.cn/organization/inclusionAI">ModelScope </a>&nbsp;&nbsp; | &nbsp;&nbsp; <a href="https://arxiv.org/abs/2606.15079">Tech Report </a></p>
 # Ling-2.6-flash-base
@@ -33,7 +34,7 @@ Ling-2.6 base models are trained through approximately 9.6T tokens across migrat
 | Item | Value |
 | --- | --- |
 | Architecture | Fine-grained MoE with hybrid linear attention |
-| Parameter Scale | Totoal ~104B, Activated ~7.4B |
 | Transformer layers | 32 |
 | Routed experts per MoE layer | 256 |
 | Shared experts per MoE layer | 1 |

 ---
 license: mit
 pipeline_tag: text-generation
+library_name: transformers
 ---
 <p align="center">
     <img src="https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*4QxcQrBlTiAAAAAAQXAAAAgAemJ7AQ/original" width="100"/>
 </p>
+<p align="center">🤗 <a href="https://huggingface.co/inclusionAI">Hugging Face</a>&nbsp;&nbsp; | &nbsp;&nbsp;🤖 <a href="https://modelscope.cn/organization/inclusionAI">ModelScope </a>&nbsp;&nbsp; | &nbsp;&nbsp; <a href="https://arxiv.org/abs/2606.15079">Tech Report </a>&nbsp;&nbsp; | &nbsp;&nbsp; 💻 <a href="https://github.com/inclusionAI/Ling-V2.5">GitHub</a></p>
 # Ling-2.6-flash-base
 | Item | Value |
 | --- | --- |
 | Architecture | Fine-grained MoE with hybrid linear attention |
+| Parameter Scale | Total ~104B, Activated ~7.4B |
 | Transformer layers | 32 |
 | Routed experts per MoE layer | 256 |
 | Shared experts per MoE layer | 1 |