Instructions to use OpenMOSS-Team/DiRL-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenMOSS-Team/DiRL-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="OpenMOSS-Team/DiRL-8B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenMOSS-Team/DiRL-8B-Instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenMOSS-Team/DiRL-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenMOSS-Team/DiRL-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMOSS-Team/DiRL-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenMOSS-Team/DiRL-8B-Instruct

SGLang

How to use OpenMOSS-Team/DiRL-8B-Instruct 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 "OpenMOSS-Team/DiRL-8B-Instruct" \
    --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": "OpenMOSS-Team/DiRL-8B-Instruct",
		"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 "OpenMOSS-Team/DiRL-8B-Instruct" \
        --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": "OpenMOSS-Team/DiRL-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenMOSS-Team/DiRL-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/OpenMOSS-Team/DiRL-8B-Instruct
```

nielsr HF Staff commited on 11 days ago

Commit

8bd5c32

verified ·

1 Parent(s): 898c2ea

Add community evaluation results for GSM8K

Browse files

This PR adds community-provided evaluation results for the following benchmarks:

- **[GSM8K](https://huggingface.co/datasets/openai/gsm8k?eval_result=OpenMOSS-Team/DiRL-8B-Instruct&leaderboard_task_id=gsm8k&leaderboard_base_model=false)**

These results were extracted from Table 1 of the [paper](https://huggingface.co/papers/2512.22234). This is based on the new [evaluation results feature](https://huggingface.co/docs/hub/eval-results).

*Note: This is an automated PR. Please review the evaluation results before merging.*

Files changed (1) hide show

.eval_results/gsm8k.yaml +7 -0

.eval_results/gsm8k.yaml ADDED Viewed

	@@ -0,0 +1,7 @@

+- dataset:
+    id: openai/gsm8k
+    task_id: gsm8k
+  value: 93.1
+  source:
+    url: https://arxiv.org/abs/2512.22234
+    name: Paper (Table 1)