Instructions to use fiveflow/r0_96 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fiveflow/r0_96 with Transformers:

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

pipe = pipeline("text-generation", model="fiveflow/r0_96")
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("fiveflow/r0_96")
model = AutoModelForCausalLM.from_pretrained("fiveflow/r0_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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fiveflow/r0_96 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fiveflow/r0_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/r0_96",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fiveflow/r0_96

SGLang

How to use fiveflow/r0_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/r0_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/r0_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/r0_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/r0_96",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fiveflow/r0_96 with Docker Model Runner:
```
docker model run hf.co/fiveflow/r0_96
```

fiveflow commited on Sep 24

Commit

75efd97

verified ·

1 Parent(s): de52895

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -29

README.md CHANGED Viewed

@@ -10,32 +10,3 @@ tags:
 - reinforcement-learning
 ---
-# 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](https://huggingface.co/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.


10	- reinforcement-learning
11	---
12