Instructions to use fiveflow/rzero_8b_96 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fiveflow/rzero_8b_96 with Transformers:

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

pipe = pipeline("text-generation", model="fiveflow/rzero_8b_96")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fiveflow/rzero_8b_96")
model = AutoModelForCausalLM.from_pretrained("fiveflow/rzero_8b_96", 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 fiveflow/rzero_8b_96 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fiveflow/rzero_8b_96"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fiveflow/rzero_8b_96",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fiveflow/rzero_8b_96

SGLang

How to use fiveflow/rzero_8b_96 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 "fiveflow/rzero_8b_96" \
    --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": "fiveflow/rzero_8b_96",
		"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 "fiveflow/rzero_8b_96" \
        --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": "fiveflow/rzero_8b_96",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fiveflow/rzero_8b_96 with Docker Model Runner:
```
docker model run hf.co/fiveflow/rzero_8b_96
```

R-Zero Qwen3-8B-Base — global step 96

This repository contains the user's R-Zero experiment checkpoint at cumulative global step 96 (round 3, round-local step 32). It is an experiment artifact, not an official release by the Qwen or R-Zero authors.

The four BF16 safetensors shards and tokenizer/configuration files are copied byte-for-byte from the existing Hugging Face-format checkpoint. The model was not loaded, merged again, or re-exported for this upload. The index contains 399 tensors and 8,190,735,360 parameters. Per-file SHA256 checksums are recorded in checkpoint_manifest.json.

The upstream base is Qwen/Qwen3-8B-Base, whose published model card identifies the Apache 2.0 license. The standard license text is included in LICENSE.

Evaluation scope

This checkpoint was selected by the recorded unweighted mean over seven prior benchmarks, not by Omni-MATH-2 scores. This upload makes no claim about its Omni-MATH-2 accuracy or its strongest/weakest domain-by-problem-type cell.

For the separate omni_math2_standalone evaluation package, use a pinned commit revision when downloading and a separate run named rzero_96. Do not use the RQ step-256 wrapper with this model: the wrapper targets rq_256.

Keep decoding and grading settings unchanged when comparing checkpoints. Generated answers may be incorrect; neither model outputs nor benchmark reference answers are guaranteed correct.

Downloads last month: 253

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for fiveflow/rzero_8b_96

Base model

Qwen/Qwen3-8B-Base

Finetuned

(548)

this model