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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("kangdawei/MMR-DAPO-8B")
model = AutoModelForMultimodalLM.from_pretrained("kangdawei/MMR-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
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

kangdawei commited on Dec 12, 2025

Commit

1a11888

verified ·

1 Parent(s): 15167ec

Model save

Browse files

Files changed (7) hide show

README.md +2 -4
adapter/adapter_config.json +3 -3
adapter/adapter_model.safetensors +1 -1
adapter/training_args.bin +1 -1
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-Llama-8B
-datasets: knoveleng/open-rs
 library_name: transformers
 model_name: MMR-DAPO-8B
 tags:
 - generated_from_trainer
-- open-r1
-- dapo
 - trl
 licence: license
 ---
 # Model Card for MMR-DAPO-8B
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) 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

 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
 library_name: transformers
 model_name: MMR-DAPO-8B
 tags:
 - generated_from_trainer
 - trl
+- dapo
 licence: license
 ---
 # Model Card for MMR-DAPO-8B
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

adapter/adapter_config.json CHANGED Viewed

@@ -29,12 +29,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
-    "o_proj",
     "q_proj",
-    "gate_proj",
     "up_proj",
-    "down_proj",
     "k_proj"
   ],
   "target_parameters": null,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "v_proj",
+    "down_proj",
     "q_proj",
     "up_proj",
+    "o_proj",
     "k_proj"
   ],
   "target_parameters": null,

adapter/adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed841ce54452bbd2d6036804b5fc85c8a834489218f2d704cbb3ca79fa3f9ee6
 size 335605144

 version https://git-lfs.github.com/spec/v1
+oid sha256:a7ee9e7c2eac5c0ab901dc35136afccb7eb66edc9f7f816cc94694bcb485013e
 size 335605144

adapter/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef370d914d9a05e49937087415db72e73a9791149e9a29c0659a2a50b73c406
 size 8760

 version https://git-lfs.github.com/spec/v1
+oid sha256:db51de36052d471fb66be30ebb6e5b6c01be64d1168c33d491244e9d7deb77aa
 size 8760

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.007976829088478937,
-    "train_runtime": 170327.2885,
     "train_samples": 7000,
-    "train_samples_per_second": 0.141,
     "train_steps_per_second": 0.003
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.004007526492219044,
+    "train_runtime": 34518.5958,
     "train_samples": 7000,
+    "train_samples_per_second": 0.139,
     "train_steps_per_second": 0.003
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.007976829088478937,
-    "train_runtime": 170327.2885,
     "train_samples": 7000,
-    "train_samples_per_second": 0.141,
     "train_steps_per_second": 0.003
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.004007526492219044,
+    "train_runtime": 34518.5958,
     "train_samples": 7000,
+    "train_samples_per_second": 0.139,
     "train_steps_per_second": 0.003
 }

trainer_state.json CHANGED Viewed

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