Instructions to use joooelw/BEHAVE-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use joooelw/BEHAVE-27B with Transformers:

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

pipe = pipeline("text-generation", model="joooelw/BEHAVE-27B")
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("joooelw/BEHAVE-27B")
model = AutoModelForMultimodalLM.from_pretrained("joooelw/BEHAVE-27B", device_map="auto")
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 joooelw/BEHAVE-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "joooelw/BEHAVE-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "joooelw/BEHAVE-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/joooelw/BEHAVE-27B

SGLang

How to use joooelw/BEHAVE-27B 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 "joooelw/BEHAVE-27B" \
    --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": "joooelw/BEHAVE-27B",
		"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 "joooelw/BEHAVE-27B" \
        --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": "joooelw/BEHAVE-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use joooelw/BEHAVE-27B with Docker Model Runner:
```
docker model run hf.co/joooelw/BEHAVE-27B
```

BEHAVE-27B

BEHAVE-27B is a model for multi-turn co-development of RTL designs and executable behavior models for verification.

This release is the HF40 checkpoint, obtained after 40 GRPO updates using the fixed 540-task BEHAVE-Train pool, starting from Qwen3.8-27B. It is the fixed-dataset RL model, not the separate self-improvement model.

Code and benchmark information: joel-wu/BEHAVE.

Checkpoint and files

The hf40 tag identifies the paper's 40-update checkpoint. The internal export is numbered hf_39 because update indices start at zero.
The release contains full model weights in 178 Safetensors shards, the weight index, model configuration, tokenizer, chat template, processor configuration, and the Apache 2.0 license.
Optimizer states, private training logs, and other checkpoints are not included.

Download

from huggingface_hub import snapshot_download

model_dir = snapshot_download(
    repo_id="joooelw/BEHAVE-27B",
    revision="hf40",
)

Use a model runtime compatible with Qwen3.8-27B and the included configuration and chat template. Reproducing the multi-turn agent evaluation also requires the BEHAVE tool environment and task settings; downloading weights alone does not reproduce those experiments.

Limitations

Generated RTL and reference models can contain errors and require independent verification before use. The model is not a replacement for hardware verification or signoff.

License

Apache 2.0. See LICENSE.

Downloads last month: 270

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for joooelw/BEHAVE-27B

Base model

Qwen/Qwen3.8-27B

Finetuned

(414)

this model