Instructions to use lllyx/Qwen3-4B-Base-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lllyx/Qwen3-4B-Base-GRPO with Transformers:

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

pipe = pipeline("text-generation", model="lllyx/Qwen3-4B-Base-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lllyx/Qwen3-4B-Base-GRPO")
model = AutoModelForCausalLM.from_pretrained("lllyx/Qwen3-4B-Base-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 lllyx/Qwen3-4B-Base-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lllyx/Qwen3-4B-Base-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": "lllyx/Qwen3-4B-Base-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lllyx/Qwen3-4B-Base-GRPO

SGLang

How to use lllyx/Qwen3-4B-Base-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 "lllyx/Qwen3-4B-Base-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": "lllyx/Qwen3-4B-Base-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 "lllyx/Qwen3-4B-Base-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": "lllyx/Qwen3-4B-Base-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lllyx/Qwen3-4B-Base-GRPO with Docker Model Runner:
```
docker model run hf.co/lllyx/Qwen3-4B-Base-GRPO
```

lllyx commited on 8 days ago

Commit

73067d4

verified ·

1 Parent(s): 141d1d0

Clarify verl RL model card

Browse files

Files changed (1) hide show

README.md +20 -11

README.md CHANGED Viewed

@@ -10,9 +10,11 @@ tags:
 - qwen3
 - math
 - grpo
 - reinforcement-learning
 - on-policy-distillation
-- full-finetuning
 - reasoning
 - safetensors
 - arxiv:2604.13016
@@ -22,7 +24,8 @@ base_model_relation: finetune
 # Qwen3-4B-Base-GRPO
-Qwen3-4B-Base-GRPO is a GRPO-trained model based on **Qwen3-4B-Base**, trained on the
 **DAPO-Math-17k-Processed** dataset for mathematical reasoning and problem-solving.
 This model is associated with the paper:
@@ -31,19 +34,22 @@ Paper link: https://arxiv.org/abs/2604.13016
 ## Model Description
-This model is obtained by full-parameter GRPO training from `Qwen3-4B-Base`.
-The training is designed to improve the model's performance on math-focused
-reasoning tasks under the on-policy distillation setting.
-No learned reward model is used in this training run. Rewards are computed by a
-custom rule-based reward function for math evaluation:
 `verl/verl/utils/reward_score/ttrl_math/__init__.py`.
 ### Key characteristics
 - **Base model**: Qwen3-4B-Base
-- **Training stage**: GRPO
-- **Finetuning type**: Full finetuning
 - **Primary domain**: Mathematical reasoning
 - **Reward model**: Not used (`reward_model.enable: false`)
 - **Custom reward function**: `reward_func`
@@ -58,6 +64,8 @@ custom rule-based reward function for math evaluation:
 - **Framework**: verl
 - **Algorithm**: `grpo`
 - **GRPO outcome weight**: `1.0`
 - **Training dataset**: `DAPO-Math-17k-Processed`
 - **Training file**: `datasets/DAPO-Math-17k-Processed/DAPO-Math.parquet`
 - **Validation datasets**: `AIME25`, `AMC23`, `AIME24`
@@ -66,11 +74,9 @@ custom rule-based reward function for math evaluation:
 - **Validation response length**: `31744`
 - **Max model length**: `32768`
 - **Rollout temperature**: `1.0`
-- **Teacher temperature**: `1.0`
 - **Repetition penalty**: `1.0`
 - **Top-k log probability**: `0`
 - **Top-k strategy**: `union`
-- **Reward weight mode**: `student_p`
 - **KL loss**: disabled
 - **Format reward**: disabled
 - **Loss aggregation**: `token-mean`
@@ -113,6 +119,9 @@ MAX_MODEL_LEN=32768
 MINI_BATCH_SIZE=64
 TEMPERATURE=1.0
 TEACHER_TEMPERATURE=1.0
 REPETITION_PENALTY=1.0
 N_RESPONSES=8

 - qwen3
 - math
 - grpo
+- verl
+- rl
 - reinforcement-learning
 - on-policy-distillation
+- full-parameter-rl
 - reasoning
 - safetensors
 - arxiv:2604.13016
 # Qwen3-4B-Base-GRPO
+Qwen3-4B-Base-GRPO is a post-RL checkpoint trained with the **verl** framework.
+It starts from **Qwen3-4B-Base** and applies GRPO on the
 **DAPO-Math-17k-Processed** dataset for mathematical reasoning and problem-solving.
 This model is associated with the paper:
 ## Model Description
+This model is obtained by applying GRPO reinforcement learning to
+`Qwen3-4B-Base` with verl. The training updates the actor model parameters and is
+intended to improve math-focused reasoning performance under the on-policy
+distillation setting.
+No learned reward model is used in this training run. In particular,
+`reward_model.enable` is set to `false`; rewards are computed by a custom
+rule-based reward function for math evaluation:
 `verl/verl/utils/reward_score/ttrl_math/__init__.py`.
 ### Key characteristics
 - **Base model**: Qwen3-4B-Base
+- **Training framework**: verl
+- **Training stage**: Reinforcement Learning (GRPO)
+- **Parameter update**: Full-parameter actor update
 - **Primary domain**: Mathematical reasoning
 - **Reward model**: Not used (`reward_model.enable: false`)
 - **Custom reward function**: `reward_func`
 - **Framework**: verl
 - **Algorithm**: `grpo`
 - **GRPO outcome weight**: `1.0`
+- **Learned reward model**: disabled (`reward_model.enable: false`)
+- **Reward source**: custom rule-based math reward function
 - **Training dataset**: `DAPO-Math-17k-Processed`
 - **Training file**: `datasets/DAPO-Math-17k-Processed/DAPO-Math.parquet`
 - **Validation datasets**: `AIME25`, `AMC23`, `AIME24`
 - **Validation response length**: `31744`
 - **Max model length**: `32768`
 - **Rollout temperature**: `1.0`
 - **Repetition penalty**: `1.0`
 - **Top-k log probability**: `0`
 - **Top-k strategy**: `union`
 - **KL loss**: disabled
 - **Format reward**: disabled
 - **Loss aggregation**: `token-mean`
 MINI_BATCH_SIZE=64
 TEMPERATURE=1.0
+# TEACHER_TEMPERATURE and REWARD_WEIGHT_MODE are rollout/logit-control settings
+# from the training script. They do not indicate the use of a learned reward model.
 TEACHER_TEMPERATURE=1.0
 REPETITION_PENALTY=1.0
 N_RESPONSES=8