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

Libraries

How to use kangdawei/MMR-DAPO with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kangdawei/MMR-DAPO")
model = AutoModelForCausalLM.from_pretrained("kangdawei/MMR-DAPO")
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

vLLM

How to use kangdawei/MMR-DAPO with vLLM:

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

kangdawei commited on Dec 11, 2025

Commit

e7f62f6

verified ·

1 Parent(s): 58ca0f8

Model save

Browse files

Files changed (4) hide show

README.md +3 -5
all_results.json +3 -3
train_results.json +3 -3
trainer_state.json +0 -0

README.md CHANGED Viewed

@@ -1,19 +1,17 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
-datasets: knoveleng/open-rs
 library_name: transformers
 model_name: MMR-DAPO
 tags:
 - generated_from_trainer
-- open-r1
-- dapo
 - trl
 licence: license
 ---
 # Model Card for MMR-DAPO
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on the [knoveleng/open-rs](https://huggingface.co/datasets/knoveleng/open-rs) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
@@ -38,7 +36,7 @@ This model was trained with DAPO, a method introduced in [DAPO: An Open-Source L
 - TRL: 0.16.0.dev0
 - Transformers: 4.57.1
-- Pytorch: 2.5.1+cu121
 - Datasets: 3.2.0
 - Tokenizers: 0.22.1

 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 library_name: transformers
 model_name: MMR-DAPO
 tags:
 - generated_from_trainer
 - trl
+- dapo
 licence: license
 ---
 # Model Card for MMR-DAPO
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 - TRL: 0.16.0.dev0
 - Transformers: 4.57.1
+- Pytorch: 2.5.1
 - Datasets: 3.2.0
 - Tokenizers: 0.22.1

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.02002632762067895,
-    "train_runtime": 76982.959,
     "train_samples": 7000,
-    "train_samples_per_second": 0.312,
     "train_steps_per_second": 0.006
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.025048209376691374,
+    "train_runtime": 15561.5871,
     "train_samples": 7000,
+    "train_samples_per_second": 0.308,
     "train_steps_per_second": 0.006
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.02002632762067895,
-    "train_runtime": 76982.959,
     "train_samples": 7000,
-    "train_samples_per_second": 0.312,
     "train_steps_per_second": 0.006
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.025048209376691374,
+    "train_runtime": 15561.5871,
     "train_samples": 7000,
+    "train_samples_per_second": 0.308,
     "train_steps_per_second": 0.006
 }

trainer_state.json CHANGED Viewed

The diff for this file is too large to render. See raw diff