Instructions to use RealSafe/RealSafe-R1-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RealSafe/RealSafe-R1-32B with Transformers:

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

pipe = pipeline("text-generation", model="RealSafe/RealSafe-R1-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RealSafe/RealSafe-R1-32B")
model = AutoModelForCausalLM.from_pretrained("RealSafe/RealSafe-R1-32B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RealSafe/RealSafe-R1-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RealSafe/RealSafe-R1-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RealSafe/RealSafe-R1-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RealSafe/RealSafe-R1-32B

SGLang

How to use RealSafe/RealSafe-R1-32B 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 "RealSafe/RealSafe-R1-32B" \
    --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": "RealSafe/RealSafe-R1-32B",
		"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 "RealSafe/RealSafe-R1-32B" \
        --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": "RealSafe/RealSafe-R1-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RealSafe/RealSafe-R1-32B with Docker Model Runner:
```
docker model run hf.co/RealSafe/RealSafe-R1-32B
```

RealSafe-R1-32B / trainer_log.jsonl

zzh6666

Upload folder using huggingface_hub

549d19c verified about 1 year ago

raw

history blame contribute delete

1.11 kB

	{"current_steps": 10, "total_steps": 56, "loss": 1.154, "lr": 4.921457902821578e-06, "epoch": 0.17582417582417584, "percentage": 17.86, "elapsed_time": "0:48:38", "remaining_time": "3:43:46"}
	{"current_steps": 20, "total_steps": 56, "loss": 0.8713, "lr": 4.093559974371725e-06, "epoch": 0.3516483516483517, "percentage": 35.71, "elapsed_time": "1:35:01", "remaining_time": "2:51:02"}
	{"current_steps": 30, "total_steps": 56, "loss": 0.762, "lr": 2.6569762988232838e-06, "epoch": 0.5274725274725275, "percentage": 53.57, "elapsed_time": "2:20:45", "remaining_time": "2:01:59"}
	{"current_steps": 40, "total_steps": 56, "loss": 0.7202, "lr": 1.160433012552508e-06, "epoch": 0.7032967032967034, "percentage": 71.43, "elapsed_time": "3:06:46", "remaining_time": "1:14:42"}
	{"current_steps": 50, "total_steps": 56, "loss": 0.6998, "lr": 1.7555878527937164e-07, "epoch": 0.8791208791208791, "percentage": 89.29, "elapsed_time": "3:54:03", "remaining_time": "0:28:05"}
	{"current_steps": 56, "total_steps": 56, "epoch": 0.9846153846153847, "percentage": 100.0, "elapsed_time": "4:42:04", "remaining_time": "0:00:00"}