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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kangdawei/DAPO-8B")
model = AutoModelForCausalLM.from_pretrained("kangdawei/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
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kangdawei/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/DAPO-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

kangdawei commited on Dec 16, 2025

Commit

8d4d569

verified ·

1 Parent(s): d4af99a

Training in progress, step 200

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:cebef1911edceeaf181b898210190b74e1149604d065b730b8d9274ef0bd6efd
 size 335605144

 version https://git-lfs.github.com/spec/v1
+oid sha256:ed5057e58d9c86f27f25bff17f93ec31710991515dde331e78b702be3b250793
 size 335605144

dynamic_sampling_log.txt CHANGED Viewed

@@ -1603,3 +1603,83 @@ Step     Attempts   Total Prompts   Valid Prompts   Efficiency
 189      4          24              6               25.0        %
 189      1          6               6               100.0       %
 189      3          18              6               33.3        %

 189      4          24              6               25.0        %
 189      1          6               6               100.0       %
 189      3          18              6               33.3        %
+190      3          18              6               33.3        %
+190      5          30              6               20.0        %
+190      8          48              6               12.5        %
+190      4          24              6               25.0        %
+190      4          24              6               25.0        %
+190      1          6               6               100.0       %
+190      1          6               6               100.0       %
+190      4          24              6               25.0        %
+191      9          54              6               11.1        %
+191      4          24              6               25.0        %
+191      4          24              6               25.0        %
+191      5          30              6               20.0        %
+191      3          18              6               33.3        %
+191      6          36              6               16.7        %
+191      1          6               6               100.0       %
+191      5          30              6               20.0        %
+192      3          18              6               33.3        %
+192      4          24              6               25.0        %
+192      2          12              6               50.0        %
+192      6          36              6               16.7        %
+192      3          18              6               33.3        %
+192      7          42              6               14.3        %
+192      4          24              6               25.0        %
+192      1          6               6               100.0       %
+193      3          18              6               33.3        %
+193      9          54              6               11.1        %
+193      3          18              6               33.3        %
+193      3          18              6               33.3        %
+193      1          6               6               100.0       %
+193      3          18              6               33.3        %
+193      8          48              6               12.5        %
+193      3          18              6               33.3        %
+194      3          18              6               33.3        %
+194      7          42              6               14.3        %
+194      2          12              6               50.0        %
+194      1          6               6               100.0       %
+194      1          6               6               100.0       %
+194      2          12              6               50.0        %
+194      8          48              6               12.5        %
+194      7          42              6               14.3        %
+195      5          30              6               20.0        %
+195      6          36              6               16.7        %
+195      1          6               6               100.0       %
+195      1          6               6               100.0       %
+195      10         60              6               10.0        %
+195      2          12              6               50.0        %
+195      3          18              6               33.3        %
+195      10         60              6               10.0        %
+196      2          12              6               50.0        %
+196      5          30              6               20.0        %
+196      4          24              6               25.0        %
+196      6          36              6               16.7        %
+196      7          42              6               14.3        %
+196      3          18              6               33.3        %
+196      2          12              6               50.0        %
+196      9          54              6               11.1        %
+197      2          12              6               50.0        %
+197      1          6               6               100.0       %
+197      6          36              6               16.7        %
+197      3          18              6               33.3        %
+197      2          12              6               50.0        %
+197      8          48              6               12.5        %
+197      2          12              6               50.0        %
+197      2          12              6               50.0        %
+198      6          36              6               16.7        %
+198      1          6               6               100.0       %
+198      1          6               6               100.0       %
+198      2          12              6               50.0        %
+198      1          6               6               100.0       %
+198      4          24              6               25.0        %
+198      2          12              6               50.0        %
+198      9          54              6               11.1        %
+199      1          6               6               100.0       %
+199      4          24              6               25.0        %
+199      4          24              6               25.0        %
+199      3          18              6               33.3        %
+199      4          24              6               25.0        %
+199      1          6               6               100.0       %
+199      4          24              6               25.0        %
+199      3          18              6               33.3        %