Instructions to use tencent/ContextPilot-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/ContextPilot-14B with Transformers:

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

pipe = pipeline("text-generation", model="tencent/ContextPilot-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tencent/ContextPilot-14B")
model = AutoModelForCausalLM.from_pretrained("tencent/ContextPilot-14B", device_map="auto")
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 tencent/ContextPilot-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/ContextPilot-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/ContextPilot-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent/ContextPilot-14B

SGLang

How to use tencent/ContextPilot-14B 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 "tencent/ContextPilot-14B" \
    --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": "tencent/ContextPilot-14B",
		"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 "tencent/ContextPilot-14B" \
        --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": "tencent/ContextPilot-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent/ContextPilot-14B with Docker Model Runner:
```
docker model run hf.co/tencent/ContextPilot-14B
```

Junrulu commited on 4 days ago

Commit

67c2cb2

verified ·

1 Parent(s): c4f8990

Update README.md

Browse files

Files changed (1) hide show

README.md +33 -0

README.md CHANGED Viewed

@@ -13,6 +13,39 @@ tags:
 **ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL**
 ContextPilot-14B is the Qwen3-14B checkpoint of **ContextPilot**, a proactive context-management framework for long-horizon language-model agents. It teaches agents to plan, maintain long-term memory, and offload less useful context while they continue reasoning and using tools. For more details, see our [paper]() and [code repository](https://github.com/Tencent/ContextPilot).
 ![ContextPilot overview](assets/contextpilot_overview.png)

 **ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL**
+<p align="center">
+  <a href="https://github.com/Tencent/ContextPilot">
+    <img
+      src="https://img.shields.io/badge/ContextPilot-GitHub-blue?logo=github"
+      alt="GitHub Repo"
+    />
+  </a>
+  <a href="https://tencent.github.io/ContextPilot/">
+    <img
+      src="https://img.shields.io/badge/ContextPilot-Live_Demo-ff725e?logo=githubpages&logoColor=white"
+      alt="ContextPilot Live Demo"
+    />
+  </a>
+  <a href="">
+    <img
+      src="https://img.shields.io/badge/ContextPilot-Paper-red?logo=arxiv&logoColor=red"
+      alt="Paper"
+    />
+  </a>
+  <a href="https://huggingface.co/collections/panzs19/contextpilot">
+    <img
+      src="https://img.shields.io/badge/ContextPilot-Models-yellow?logo=huggingface&logoColor=yellow"
+      alt="Hugging Face Models"
+    />
+  </a>
+  <a href="https://github.com/Tencent/ContextPilot/tree/main#setup">
+    <img
+      src="https://img.shields.io/badge/ContextPilot-Quickstart-purple?logo=rocket&logoColor=purple"
+      alt="Quickstart"
+    />
+  </a>
+</p>
 ContextPilot-14B is the Qwen3-14B checkpoint of **ContextPilot**, a proactive context-management framework for long-horizon language-model agents. It teaches agents to plan, maintain long-term memory, and offload less useful context while they continue reasoning and using tools. For more details, see our [paper]() and [code repository](https://github.com/Tencent/ContextPilot).
 ![ContextPilot overview](assets/contextpilot_overview.png)