Instructions to use Kndy666/CoACT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kndy666/CoACT with Transformers:

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

pipe = pipeline("text-generation", model="Kndy666/CoACT")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Kndy666/CoACT")
model = AutoModelForMultimodalLM.from_pretrained("Kndy666/CoACT")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kndy666/CoACT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kndy666/CoACT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kndy666/CoACT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kndy666/CoACT

SGLang

How to use Kndy666/CoACT 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 "Kndy666/CoACT" \
    --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": "Kndy666/CoACT",
		"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 "Kndy666/CoACT" \
        --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": "Kndy666/CoACT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kndy666/CoACT with Docker Model Runner:
```
docker model run hf.co/Kndy666/CoACT
```

Kndy666 commited on 1 day ago

Commit

fd8e4a2

verified ·

1 Parent(s): 66ecbd2

docs: clarify cross-agent checkpoint transfer

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -25,8 +25,10 @@ agentic models achieve similar performance when transferred across agents. When
 with Deepseek-v4-Pro, the compressor trained from Qwen3.5-35B-A3B trajectories achieves
 74.5% pass@1 with 0.863M total tokens per instance, close to 75.0% pass@1 and 0.868M total
 tokens for the compressor trained from Deepseek-v4-Pro trajectories. These results suggest
-that a separately trained compressor is not required for each agentic model; this checkpoint
-is therefore released as the default CoACT compressor for use across agentic models.
 ## Download

 with Deepseek-v4-Pro, the compressor trained from Qwen3.5-35B-A3B trajectories achieves
 74.5% pass@1 with 0.863M total tokens per instance, close to 75.0% pass@1 and 0.868M total
 tokens for the compressor trained from Deepseek-v4-Pro trajectories. These results suggest
+that this checkpoint can be used across agentic models without separately training a
+compressor for each one, while agent-specific training may still provide a small performance
+advantage. We therefore release it as the default CoACT compressor for use across agentic
+models.
 ## Download