Instructions to use rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO with Transformers:

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

pipe = pipeline("text-generation", model="rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO")
model = AutoModelForCausalLM.from_pretrained("rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO")
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 rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO

SGLang

How to use rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO 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 "rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO" \
    --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": "rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO",
		"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 "rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO" \
        --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": "rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO with Docker Model Runner:
```
docker model run hf.co/rasdani/Qwen2.5-0.5B-Open-R1-Code-GRPO
```

rasdani commited on Mar 8, 2025

Commit

a32dd19

verified ·

1 Parent(s): aca93e1

Training in progress, step 100

Browse files

Files changed (4) hide show

config.json +2 -2
model.safetensors +1 -1
tokenizer_config.json +1 -1
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 4864,
   "max_position_embeddings": 32768,
-  "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 14,
   "num_hidden_layers": 24,

 {
+  "_name_or_path": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "initializer_range": 0.02,
   "intermediate_size": 4864,
   "max_position_embeddings": 32768,
+  "max_window_layers": 24,
   "model_type": "qwen2",
   "num_attention_heads": 14,
   "num_hidden_layers": 24,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ee99008cb4e87a2f3491576cf084863f9065b9d990c4f56cba705c24325c2c1
 size 1260367448

 version https://git-lfs.github.com/spec/v1
+oid sha256:61890ffd63d404e99b32d294e3d29a00fd4500e8c6ed0425d414dfaabc704078
 size 1260367448

tokenizer_config.json CHANGED Viewed

@@ -200,7 +200,7 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d547e70a2085971351f640a9aa1d8cbafc940de687b0e84caebdc776e867fc0
 size 8120

 version https://git-lfs.github.com/spec/v1
+oid sha256:a9a612c710f0bf70bf6aeb0a88d62d8be2de57cfebf04c4b04ccf6b14689f3c6
 size 8120