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 14, 2025

Commit

5305c47

verified ·

1 Parent(s): 1730571

Training in progress, step 100

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 sha256:737947296bde632b56480be0a79326ce128a1469fd0749c69e5a1470288f632a
 size 335605144

 version https://git-lfs.github.com/spec/v1
+oid sha256:acd4f3898bf8ee245ae91ce4344cd569e84b3d9c53903bab551ff185e22fe7e4
 size 335605144

dynamic_sampling_log.txt CHANGED Viewed

@@ -734,3 +734,83 @@ Step     Attempts   Total Prompts   Valid Prompts   Efficiency
 89       4          24              6               25.0        %
 89       5          30              6               20.0        %
 89       2          12              6               50.0        %

 89       4          24              6               25.0        %
 89       5          30              6               20.0        %
 89       2          12              6               50.0        %
+90       2          12              6               50.0        %
+90       3          18              6               33.3        %
+90       8          48              6               12.5        %
+90       3          18              6               33.3        %
+90       1          6               6               100.0       %
+90       1          6               6               100.0       %
+90       2          12              6               50.0        %
+90       3          18              6               33.3        %
+91       1          6               6               100.0       %
+91       6          36              6               16.7        %
+91       4          24              6               25.0        %
+91       2          12              6               50.0        %
+91       11         66              6               9.1         %
+91       2          12              6               50.0        %
+91       7          42              6               14.3        %
+91       5          30              6               20.0        %
+92       4          24              6               25.0        %
+92       3          18              6               33.3        %
+92       3          18              6               33.3        %
+92       6          36              6               16.7        %
+92       1          6               6               100.0       %
+92       5          30              6               20.0        %
+92       3          18              6               33.3        %
+92       6          36              6               16.7        %
+93       5          30              6               20.0        %
+93       4          24              6               25.0        %
+93       2          12              6               50.0        %
+93       4          24              6               25.0        %
+93       3          18              6               33.3        %
+93       2          12              6               50.0        %
+93       5          30              6               20.0        %
+93       1          6               6               100.0       %
+94       5          30              6               20.0        %
+94       6          36              6               16.7        %
+94       7          42              6               14.3        %
+94       2          12              6               50.0        %
+94       3          18              6               33.3        %
+94       6          36              6               16.7        %
+94       6          36              6               16.7        %
+94       4          24              6               25.0        %
+95       1          6               6               100.0       %
+95       2          12              6               50.0        %
+95       3          18              6               33.3        %
+95       4          24              6               25.0        %
+95       3          18              6               33.3        %
+95       4          24              6               25.0        %
+95       3          18              6               33.3        %
+95       2          12              6               50.0        %
+96       4          24              6               25.0        %
+96       2          12              6               50.0        %
+96       5          30              6               20.0        %
+96       6          36              6               16.7        %
+96       1          6               6               100.0       %
+96       3          18              6               33.3        %
+96       2          12              6               50.0        %
+96       9          54              6               11.1        %
+97       6          36              6               16.7        %
+97       2          12              6               50.0        %
+97       5          30              6               20.0        %
+97       7          42              6               14.3        %
+97       1          6               6               100.0       %
+97       2          12              6               50.0        %
+97       8          48              6               12.5        %
+97       7          42              6               14.3        %
+98       3          18              6               33.3        %
+98       3          18              6               33.3        %
+98       3          18              6               33.3        %
+98       3          18              6               33.3        %
+98       2          12              6               50.0        %
+98       4          24              6               25.0        %
+98       1          6               6               100.0       %
+98       8          48              6               12.5        %
+99       2          12              6               50.0        %
+99       3          18              6               33.3        %
+99       11         66              6               9.1         %
+99       4          24              6               25.0        %
+99       8          48              6               12.5        %
+99       3          18              6               33.3        %
+99       2          12              6               50.0        %
+99       3          18              6               33.3        %