Instructions to use kangdawei/MMR-DAPO-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kangdawei/MMR-DAPO-8B with Transformers:

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

pipe = pipeline("text-generation", model="kangdawei/MMR-DAPO-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("kangdawei/MMR-DAPO-8B")
model = AutoModelForMultimodalLM.from_pretrained("kangdawei/MMR-DAPO-8B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kangdawei/MMR-DAPO-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kangdawei/MMR-DAPO-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kangdawei/MMR-DAPO-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kangdawei/MMR-DAPO-8B

SGLang

How to use kangdawei/MMR-DAPO-8B 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 "kangdawei/MMR-DAPO-8B" \
    --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": "kangdawei/MMR-DAPO-8B",
		"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 "kangdawei/MMR-DAPO-8B" \
        --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": "kangdawei/MMR-DAPO-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kangdawei/MMR-DAPO-8B with Docker Model Runner:
```
docker model run hf.co/kangdawei/MMR-DAPO-8B
```

MMR-DAPO-8B

Commit History

Add merged model for training step 350 (adapter revision: e123fde7)

aa3b689
verified

kangdawei commited on Dec 9, 2025

Add merged model for training step 300 (adapter revision: e01ef032)

f6d14a4
verified

kangdawei commited on Dec 9, 2025

Add merged model for training step 250 (adapter revision: 36a597b3)

b16cafe
verified

kangdawei commited on Dec 9, 2025

Add merged model for training step 200 (adapter revision: ef6852af)

1643e07
verified

kangdawei commited on Dec 9, 2025

Add merged model for training step 150 (adapter revision: 962066cb)

ed4d4fd
verified

kangdawei commited on Dec 9, 2025

Add merged model for training step 100 (adapter revision: bdd71d4c)

1fe7334
verified

kangdawei commited on Dec 9, 2025

Add merged model for training step 50 (adapter revision: 5981017d)

ea40a8f
verified

kangdawei commited on Dec 9, 2025

End of training

bc76ba3
verified

kangdawei commited on Dec 9, 2025

Model save

29319f4
verified

kangdawei commited on Dec 9, 2025

Training in progress, step 500

acdd43e
verified

kangdawei commited on Dec 9, 2025

Training in progress, step 450

a26ae4d
verified

kangdawei commited on Dec 9, 2025

Training in progress, step 400

322da0d
verified

kangdawei commited on Dec 9, 2025

Training in progress, step 350

e123fde
verified

kangdawei commited on Dec 9, 2025

Training in progress, step 300

e01ef03
verified

kangdawei commited on Dec 9, 2025

Training in progress, step 250

36a597b
verified

kangdawei commited on Dec 8, 2025

Training in progress, step 200

ef6852a
verified

kangdawei commited on Dec 8, 2025

Training in progress, step 150

962066c
verified

kangdawei commited on Dec 8, 2025

Training in progress, step 100

bdd71d4
verified

kangdawei commited on Dec 8, 2025

Training in progress, step 50

5981017
verified

kangdawei commited on Dec 8, 2025

initial commit

c8e3919
verified

kangdawei commited on Dec 7, 2025

Commit History

Add merged model for training step 350 (adapter revision: e123fde7) aa3b689 verified

Add merged model for training step 300 (adapter revision: e01ef032) f6d14a4 verified

Add merged model for training step 250 (adapter revision: 36a597b3) b16cafe verified

Add merged model for training step 200 (adapter revision: ef6852af) 1643e07 verified

Add merged model for training step 150 (adapter revision: 962066cb) ed4d4fd verified

Add merged model for training step 100 (adapter revision: bdd71d4c) 1fe7334 verified

Add merged model for training step 50 (adapter revision: 5981017d) ea40a8f verified

End of training bc76ba3 verified

Model save 29319f4 verified

Training in progress, step 500 acdd43e verified

Training in progress, step 450 a26ae4d verified

Training in progress, step 400 322da0d verified

Training in progress, step 350 e123fde verified

Training in progress, step 300 e01ef03 verified

Training in progress, step 250 36a597b verified

Training in progress, step 200 ef6852a verified

Training in progress, step 150 962066c verified

Training in progress, step 100 bdd71d4 verified

Training in progress, step 50 5981017 verified

initial commit c8e3919 verified

Add merged model for training step 350 (adapter revision: e123fde7)

aa3b689
verified

Add merged model for training step 300 (adapter revision: e01ef032)

f6d14a4
verified

Add merged model for training step 250 (adapter revision: 36a597b3)

b16cafe
verified

Add merged model for training step 200 (adapter revision: ef6852af)

1643e07
verified

Add merged model for training step 150 (adapter revision: 962066cb)

ed4d4fd
verified

Add merged model for training step 100 (adapter revision: bdd71d4c)

1fe7334
verified

Add merged model for training step 50 (adapter revision: 5981017d)

ea40a8f
verified

End of training

bc76ba3
verified

Model save

29319f4
verified

Training in progress, step 500

acdd43e
verified

Training in progress, step 450

a26ae4d
verified

Training in progress, step 400

322da0d
verified

Training in progress, step 350

e123fde
verified

Training in progress, step 300

e01ef03
verified

Training in progress, step 250

36a597b
verified

Training in progress, step 200

ef6852a
verified

Training in progress, step 150

962066c
verified

Training in progress, step 100

bdd71d4
verified

Training in progress, step 50

5981017
verified

initial commit

c8e3919
verified