Instructions to use Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill with Transformers:

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

pipe = pipeline("text-generation", model="Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill")
model = AutoModelForCausalLM.from_pretrained("Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill", device_map="auto")
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 Settings

vLLM

How to use Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill

SGLang

How to use Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill 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 "Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill" \
    --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": "Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill",
		"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 "Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill" \
        --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": "Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill with Docker Model Runner:
```
docker model run hf.co/Sunnylululu/Qwen2.5-1.5B-Open-R1-Distill
```

Qwen2.5-1.5B-Open-R1-Distill / trainer_state.json

Sunnylululu

Model save

cbd622e verified over 1 year ago

Raw

History Blame Contribute Delete

5.18 kB

	{
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 10.0,
	"eval_steps": 500,
	"global_step": 130,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.38461538461538464,
	"grad_norm": 2.234375,
	"learning_rate": 3.571428571428572e-05,
	"loss": 1.3998,
	"step": 5
	},
	{
	"epoch": 0.7692307692307693,
	"grad_norm": 1.203125,
	"learning_rate": 4.993398052663416e-05,
	"loss": 1.2457,
	"step": 10
	},
	{
	"epoch": 1.1538461538461537,
	"grad_norm": 0.75390625,
	"learning_rate": 4.953193036870676e-05,
	"loss": 1.0969,
	"step": 15
	},
	{
	"epoch": 1.5384615384615383,
	"grad_norm": 0.66796875,
	"learning_rate": 4.877104772313846e-05,
	"loss": 1.0383,
	"step": 20
	},
	{
	"epoch": 1.9230769230769231,
	"grad_norm": 0.5859375,
	"learning_rate": 4.766372503162375e-05,
	"loss": 0.9794,
	"step": 25
	},
	{
	"epoch": 2.3076923076923075,
	"grad_norm": 0.57421875,
	"learning_rate": 4.622799718031961e-05,
	"loss": 0.9258,
	"step": 30
	},
	{
	"epoch": 2.6923076923076925,
	"grad_norm": 0.578125,
	"learning_rate": 4.448724776693342e-05,
	"loss": 0.9013,
	"step": 35
	},
	{
	"epoch": 3.076923076923077,
	"grad_norm": 0.609375,
	"learning_rate": 4.246982825372522e-05,
	"loss": 0.8851,
	"step": 40
	},
	{
	"epoch": 3.4615384615384617,
	"grad_norm": 0.53515625,
	"learning_rate": 4.020859620925235e-05,
	"loss": 0.8483,
	"step": 45
	},
	{
	"epoch": 3.8461538461538463,
	"grad_norm": 0.5625,
	"learning_rate": 3.77403801594802e-05,
	"loss": 0.8315,
	"step": 50
	},
	{
	"epoch": 4.230769230769231,
	"grad_norm": 0.5390625,
	"learning_rate": 3.510537976419131e-05,
	"loss": 0.8181,
	"step": 55
	},
	{
	"epoch": 4.615384615384615,
	"grad_norm": 0.5234375,
	"learning_rate": 3.234651108797708e-05,
	"loss": 0.7815,
	"step": 60
	},
	{
	"epoch": 5.0,
	"grad_norm": 0.81640625,
	"learning_rate": 2.9508707629336874e-05,
	"loss": 0.8063,
	"step": 65
	},
	{
	"epoch": 5.384615384615385,
	"grad_norm": 0.52734375,
	"learning_rate": 2.6638188491974207e-05,
	"loss": 0.7603,
	"step": 70
	},
	{
	"epoch": 5.769230769230769,
	"grad_norm": 0.53125,
	"learning_rate": 2.378170561753209e-05,
	"loss": 0.7657,
	"step": 75
	},
	{
	"epoch": 6.153846153846154,
	"grad_norm": 0.55078125,
	"learning_rate": 2.098578234003466e-05,
	"loss": 0.749,
	"step": 80
	},
	{
	"epoch": 6.538461538461538,
	"grad_norm": 0.50390625,
	"learning_rate": 1.8295955663644855e-05,
	"loss": 0.7504,
	"step": 85
	},
	{
	"epoch": 6.923076923076923,
	"grad_norm": 0.447265625,
	"learning_rate": 1.575603460470665e-05,
	"loss": 0.7376,
	"step": 90
	},
	{
	"epoch": 7.3076923076923075,
	"grad_norm": 0.474609375,
	"learning_rate": 1.3407386677402312e-05,
	"loss": 0.7354,
	"step": 95
	},
	{
	"epoch": 7.6923076923076925,
	"grad_norm": 0.447265625,
	"learning_rate": 1.1288264143982296e-05,
	"loss": 0.7365,
	"step": 100
	},
	{
	"epoch": 8.076923076923077,
	"grad_norm": 0.4609375,
	"learning_rate": 9.433181002882383e-06,
	"loss": 0.731,
	"step": 105
	},
	{
	"epoch": 8.461538461538462,
	"grad_norm": 0.443359375,
	"learning_rate": 7.872350861678565e-06,
	"loss": 0.7102,
	"step": 110
	},
	{
	"epoch": 8.846153846153847,
	"grad_norm": 0.443359375,
	"learning_rate": 6.631194850202872e-06,
	"loss": 0.7296,
	"step": 115
	},
	{
	"epoch": 9.23076923076923,
	"grad_norm": 0.416015625,
	"learning_rate": 5.729927588404395e-06,
	"loss": 0.7268,
	"step": 120
	},
	{
	"epoch": 9.615384615384615,
	"grad_norm": 0.41796875,
	"learning_rate": 5.1832279522675925e-06,
	"loss": 0.7262,
	"step": 125
	},
	{
	"epoch": 10.0,
	"grad_norm": 0.77734375,
	"learning_rate": 5e-06,
	"loss": 0.7346,
	"step": 130
	},
	{
	"epoch": 10.0,
	"step": 130,
	"total_flos": 2.5375909456379904e+17,
	"train_loss": 0.0,
	"train_runtime": 2.0428,
	"train_samples_per_second": 964.355,
	"train_steps_per_second": 63.638
	}
	],
	"logging_steps": 5,
	"max_steps": 130,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 10,
	"save_steps": 10,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": true
	},
	"attributes": {}
	}
	},
	"total_flos": 2.5375909456379904e+17,
	"train_batch_size": 16,
	"trial_name": null,
	"trial_params": null
	}