Instructions to use kangdawei/DAPO-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kangdawei/DAPO-7B with Transformers:

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

pipe = pipeline("text-generation", model="kangdawei/DAPO-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kangdawei/DAPO-7B")
model = AutoModelForCausalLM.from_pretrained("kangdawei/DAPO-7B")
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
Local Apps Settings

vLLM

How to use kangdawei/DAPO-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kangdawei/DAPO-7B"
# 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/DAPO-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kangdawei/DAPO-7B

SGLang

How to use kangdawei/DAPO-7B 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/DAPO-7B" \
    --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/DAPO-7B",
		"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/DAPO-7B" \
        --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/DAPO-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kangdawei/DAPO-7B with Docker Model Runner:
```
docker model run hf.co/kangdawei/DAPO-7B
```

kangdawei commited on Dec 13, 2025

Commit

f3a786b

verified ·

1 Parent(s): 834962b

Training in progress, step 90

Browse files

Files changed (2) hide show

adapter_model.safetensors +1 -1
dynamic_sampling_log.txt +80 -0

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bffb47daaf8b258a0fee8b83cca970c428d15021cd8894d085e6d620b1dbe9e0
 size 323014560

 version https://git-lfs.github.com/spec/v1
+oid sha256:45102f3d0689a3540b9e8de2776ec867b822e056f444363167f4089f53d3becb
 size 323014560

dynamic_sampling_log.txt CHANGED Viewed

@@ -643,3 +643,83 @@ Step     Attempts   Total Prompts   Valid Prompts   Efficiency
 79       3          18              6               33.3        %
 79       1          6               6               100.0       %
 79       2          12              6               50.0        %

 79       3          18              6               33.3        %
 79       1          6               6               100.0       %
 79       2          12              6               50.0        %
+80       3          18              6               33.3        %
+80       3          18              6               33.3        %
+80       2          12              6               50.0        %
+80       2          12              6               50.0        %
+80       2          12              6               50.0        %
+80       1          6               6               100.0       %
+80       1          6               6               100.0       %
+80       3          18              6               33.3        %
+81       3          18              6               33.3        %
+81       2          12              6               50.0        %
+81       3          18              6               33.3        %
+81       4          24              6               25.0        %
+81       6          36              6               16.7        %
+81       1          6               6               100.0       %
+81       3          18              6               33.3        %
+81       2          12              6               50.0        %
+82       5          30              6               20.0        %
+82       2          12              6               50.0        %
+82       4          24              6               25.0        %
+82       2          12              6               50.0        %
+82       3          18              6               33.3        %
+82       1          6               6               100.0       %
+82       2          12              6               50.0        %
+82       2          12              6               50.0        %
+83       2          12              6               50.0        %
+83       3          18              6               33.3        %
+83       2          12              6               50.0        %
+83       3          18              6               33.3        %
+83       4          24              6               25.0        %
+83       2          12              6               50.0        %
+83       3          18              6               33.3        %
+83       2          12              6               50.0        %
+84       4          24              6               25.0        %
+84       3          18              6               33.3        %
+84       2          12              6               50.0        %
+84       1          6               6               100.0       %
+84       3          18              6               33.3        %
+84       2          12              6               50.0        %
+84       3          18              6               33.3        %
+84       2          12              6               50.0        %
+85       2          12              6               50.0        %
+85       2          12              6               50.0        %
+85       4          24              6               25.0        %
+85       2          12              6               50.0        %
+85       1          6               6               100.0       %
+85       1          6               6               100.0       %
+85       3          18              6               33.3        %
+85       6          36              6               16.7        %
+86       2          12              6               50.0        %
+86       2          12              6               50.0        %
+86       3          18              6               33.3        %
+86       5          30              6               20.0        %
+86       6          36              6               16.7        %
+86       4          24              6               25.0        %
+86       6          36              6               16.7        %
+86       1          6               6               100.0       %
+87       3          18              6               33.3        %
+87       6          36              6               16.7        %
+87       4          24              6               25.0        %
+87       2          12              6               50.0        %
+87       4          24              6               25.0        %
+87       7          42              6               14.3        %
+87       5          30              6               20.0        %
+87       5          30              6               20.0        %
+88       2          12              6               50.0        %
+88       1          6               6               100.0       %
+88       2          12              6               50.0        %
+88       3          18              6               33.3        %
+88       3          18              6               33.3        %
+88       3          18              6               33.3        %
+88       2          12              6               50.0        %
+88       3          18              6               33.3        %
+89       2          12              6               50.0        %
+89       2          12              6               50.0        %
+89       2          12              6               50.0        %
+89       3          18              6               33.3        %
+89       1          6               6               100.0       %
+89       3          18              6               33.3        %
+89       5          30              6               20.0        %
+89       3          18              6               33.3        %