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

e9530ed

verified ·

1 Parent(s): 1d83e99

Training in progress, step 110

Browse files

Files changed (3) hide show

adapter_model.safetensors +1 -1
dynamic_sampling_log.txt +80 -0
tokenizer.json +2 -2

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd4f3898bf8ee245ae91ce4344cd569e84b3d9c53903bab551ff185e22fe7e4
 size 335605144

 version https://git-lfs.github.com/spec/v1
+oid sha256:b23e260d1a699c66322c5d307a7fc4ca9da7873e4615727d1a51806a976013dd
 size 335605144

dynamic_sampling_log.txt CHANGED Viewed

@@ -814,3 +814,83 @@ Step     Attempts   Total Prompts   Valid Prompts   Efficiency
 99       3          18              6               33.3        %
 99       2          12              6               50.0        %
 99       3          18              6               33.3        %

 99       3          18              6               33.3        %
 99       2          12              6               50.0        %
 99       3          18              6               33.3        %
+100      2          12              6               50.0        %
+100      3          18              6               33.3        %
+100      3          18              6               33.3        %
+100      3          18              6               33.3        %
+100      1          6               6               100.0       %
+100      6          36              6               16.7        %
+100      3          18              6               33.3        %
+100      2          12              6               50.0        %
+101      3          18              6               33.3        %
+101      4          24              6               25.0        %
+101      4          24              6               25.0        %
+101      5          30              6               20.0        %
+101      4          24              6               25.0        %
+101      3          18              6               33.3        %
+101      1          6               6               100.0       %
+101      2          12              6               50.0        %
+102      5          30              6               20.0        %
+102      2          12              6               50.0        %
+102      2          12              6               50.0        %
+102      3          18              6               33.3        %
+102      3          18              6               33.3        %
+102      4          24              6               25.0        %
+102      6          36              6               16.7        %
+102      6          36              6               16.7        %
+103      3          18              6               33.3        %
+103      1          6               6               100.0       %
+103      7          42              6               14.3        %
+103      8          48              6               12.5        %
+103      6          36              6               16.7        %
+103      3          18              6               33.3        %
+103      3          18              6               33.3        %
+103      6          36              6               16.7        %
+104      3          18              6               33.3        %
+104      1          6               6               100.0       %
+104      2          12              6               50.0        %
+104      2          12              6               50.0        %
+104      5          30              6               20.0        %
+104      5          30              6               20.0        %
+104      5          30              6               20.0        %
+104      1          6               6               100.0       %
+105      8          48              6               12.5        %
+105      2          12              6               50.0        %
+105      3          18              6               33.3        %
+105      4          24              6               25.0        %
+105      6          36              6               16.7        %
+105      3          18              6               33.3        %
+105      4          24              6               25.0        %
+105      2          12              6               50.0        %
+106      4          24              6               25.0        %
+106      4          24              6               25.0        %
+106      4          24              6               25.0        %
+106      11         66              6               9.1         %
+106      5          30              6               20.0        %
+106      3          18              6               33.3        %
+106      5          30              6               20.0        %
+106      9          54              6               11.1        %
+107      6          36              6               16.7        %
+107      10         60              6               10.0        %
+107      7          42              6               14.3        %
+107      5          30              6               20.0        %
+107      4          24              6               25.0        %
+107      5          30              6               20.0        %
+107      2          12              6               50.0        %
+107      6          36              6               16.7        %
+108      1          6               6               100.0       %
+108      1          6               6               100.0       %
+108      4          24              6               25.0        %
+108      3          18              6               33.3        %
+108      11         66              6               9.1         %
+108      1          6               6               100.0       %
+108      4          24              6               25.0        %
+108      1          6               6               100.0       %
+109      2          12              6               50.0        %
+109      1          6               6               100.0       %
+109      2          12              6               50.0        %
+109      2          12              6               50.0        %
+109      10         60              6               10.0        %
+109      5          30              6               20.0        %
+109      3          18              6               33.3        %
+109      5          30              6               20.0        %

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
-size 17209530

 version https://git-lfs.github.com/spec/v1
+oid sha256:26c881aaf4ef935b1516ec79ad6405dd2a459f2b5d431a8a4a1399c92f3ba022
+size 17209711