Instructions to use yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro with Transformers:

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

pipe = pipeline("text-generation", model="yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro")
model = AutoModelForCausalLM.from_pretrained("yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro

SGLang

How to use yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro 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 "yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro" \
    --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": "yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro",
		"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 "yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro" \
        --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": "yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro with Docker Model Runner:
```
docker model run hf.co/yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro
```

verl-GRPO CollabLLM medium — Qwen3-4B, step 129 (reproduction)

Independent-cluster reproduction of yuhan-nlp/verl-grpo-medium-qwen3-4b-step129: same recipe, same data, different hardware.

Qwen/Qwen3-4B trained with GRPO on the CollabLLM medium document-writing task using the verl CollabLLM recipe (no SFT warm start). Merged HF checkpoint — load it directly, no adapter step.

Provenance


merged from	`collabllm-qwen3-4B-medium-large-epoch1/global_step_129/actor` (8-shard FSDP)
merged with	`python -m verl.model_merger merge --backend fsdp`
training data	yuhan-nlp/collabllm-medium-rl-grpo

Evaluation

No metrics are reported here on purpose. The benchmark runs backing this checkpoint — per-example traces, judge outputs and summary JSON — live in yuhan-nlp/collabllm-medium-outputs under benchmark_runs/, which is the single source of truth for the numbers.

Setup used there: assistant = this model, user simulator Qwen/Qwen3.5-9B, judge Qwen/Qwen3.5-27B, thinking off everywhere, --user_sim_prompt sim_gap_paper_lazy_full --assistant_max_tokens 4096 --max_new_turns 14, --eval_size 100.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
rid = "yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro"
tok = AutoTokenizer.from_pretrained(rid)
model = AutoModelForCausalLM.from_pretrained(rid, dtype="bfloat16", device_map="auto")

The chat template ships as chat_template.jinja (transformers >= 4.57 keeps it out of tokenizer_config.json); AutoTokenizer picks it up automatically.

Downloads last month: 26

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

(1150)

this model

yuhan-nlp
/

verl-grpo-medium-qwen3-4b-step129-repro

verl-GRPO CollabLLM medium — Qwen3-4B, step 129 (reproduction)

Provenance

Evaluation

Usage

Model tree for yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro

Dataset used to train yuhan-nlp/verl-grpo-medium-qwen3-4b-step129-repro