Instructions to use CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500 with Transformers:

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

pipe = pipeline("text-generation", model="CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500")
model = AutoModelForCausalLM.from_pretrained("CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500", 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 CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500

SGLang

How to use CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500 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 "CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500" \
    --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": "CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500",
		"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 "CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500" \
        --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": "CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500 with Docker Model Runner:
```
docker model run hf.co/CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500
```

Qwen3-4B SSD (RLVE Eval20, N=20) — global step 500

Weights merged from VERL FSDP SFT checkpoint global_step_500 (500 optimizer steps, 1 epoch schedule) of Simple Self-Distillation (SSD) applied to Qwen/Qwen3-4B: sample N=20 self-generated responses from the frozen base model, then SFT on those samples.

Training data

Parquet SFT corpus (16k rows, messages column): CL-From-Nothing/RLVE-Eval20-Qwen3-4B-SSD-N20-SFT-Train.

Companion 1.7B model: CL-From-Nothing/Qwen3-1-7B-SSD-RLVE-Eval20-N20-global-step-500.

Load

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

Downloads last month: 27

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

(1077)

this model