Instructions to use FinStep/Alpha-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FinStep/Alpha-R1 with Transformers:

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

pipe = pipeline("text-generation", model="FinStep/Alpha-R1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FinStep/Alpha-R1")
model = AutoModelForCausalLM.from_pretrained("FinStep/Alpha-R1", 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 FinStep/Alpha-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FinStep/Alpha-R1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FinStep/Alpha-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FinStep/Alpha-R1

SGLang

How to use FinStep/Alpha-R1 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 "FinStep/Alpha-R1" \
    --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": "FinStep/Alpha-R1",
		"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 "FinStep/Alpha-R1" \
        --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": "FinStep/Alpha-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FinStep/Alpha-R1 with Docker Model Runner:
```
docker model run hf.co/FinStep/Alpha-R1
```

Alpha-R1 / README.md

iamzuoyou

Update README.md: add hero image below title

f163935 verified 2 days ago

preview code

Raw

History Blame Contribute Delete

6.66 kB

	---
	license: mit
	base_model: Qwen/Qwen3-8B
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- finance
	- quantitative-trading
	- alpha-factor
	- reinforcement-learning
	- grpo
	- qlib
	---

	# Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning

	<p align="center">
	<img src="assets/Alpha-R1.png" alt="Alpha-R1" style="width: 100%; height: auto;">
	</p>

	<p align="center">
	<a href="https://huggingface.co/FinStep/Alpha-R1/blob/main/README_en.md">English</a> \| <a href="https://huggingface.co/FinStep/Alpha-R1/blob/main/README.md">中文</a>
	</p>

	Alpha-R1 是一个面向量化 Alpha 筛选的推理增强型 LLM：基于 Qwen3-8B，通过 GRPO 强化学习（[verl](https://github.com/volcengine/verl)）以市场反馈奖励训练。它阅读 Alpha101 因子的语义化描述——每个因子如何起作用、何时有效、何时失效——并针对当前市场环境筛选出最值得激活的因子组合。

	- 📄 Paper: [arXiv:2512.23515](https://arxiv.org/abs/2512.23515)
	- 💻 Code: [FinStep-AI/Alpha-R1](https://github.com/FinStep-AI/Alpha-R1)（推理管线 / qlib 回测 / 训练配置）
	- 📜 License: MIT

	## 模型概览 (Model Overview)

	<p align="center">
	<img src="assets/framework.png" alt="Alpha-R1 framework overview" style="width: 100%;">
	</p>

	\| 项目 \| 内容 \|
	\|---\|---\|
	\| Base model \| [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) \|
	\| 训练方法 \| GRPO（verl），市场反馈奖励 \|
	\| 输入 \| 决策上下文 prompt：拼接的因子语义描述 `α_des` \|
	\| 输出 \| `<alpha_list>` 中列出的选中因子 \|
	\| 候选因子池 \| 82 个 Alpha101 因子（论文筛选后） \|
	\| 推荐解码 \| temperature=0（greedy），top_p=0.7，max_new_tokens=4096 \|

	## 快速开始 (Quick Start)

	### transformers

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_id = "FinStep/Alpha-R1"
	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(model_id, dtype="bfloat16", device_map="auto")

	prompt = "<decision context: concatenated factor descriptions>" # see the GitHub repo for the prompt builder
	inputs = tokenizer.apply_chat_template(
	[{"role": "user", "content": prompt}],
	add_generation_prompt=True, return_tensors="pt",
	).to(model.device)

	# paper setting: temperature=0 (greedy), top_p=0.7
	out = model.generate(inputs, max_new_tokens=4096, do_sample=False)
	print(tokenizer.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))
	```

	### vLLM

	```python
	from vllm import LLM, SamplingParams

	llm = LLM(model="FinStep/Alpha-R1")
	params = SamplingParams(temperature=0.0, top_p=0.7, max_tokens=4096)
	outputs = llm.chat([[{"role": "user", "content": prompt}]], params)
	```

	完整的端到端管线（因子描述生成 → Alpha-R1 推理 → 输出解析 → qlib 策略回测）见 [GitHub 仓库](https://github.com/FinStep-AI/Alpha-R1)。

	## 输出契约 (Output Contract)

	模型在 `<alpha_list>...</alpha_list>` 中输出选中的因子 id，例如：

	```
	<alpha_list>alpha001, alpha021, alpha053</alpha_list>
	```

	GitHub 仓库的 `src/alpha_r1/parsing/` 提供了配套的校验与解析脚本。

	## 表现 (Performance)

	12 个月样本外测试（2025-01-01 ~ 2025-12-31，论文 Table 1）：

	<p align="center">
	<img src="assets/main_results.png" alt="Backtest NAV comparison on S&P 500 (left) and CSI 300 (right)" style="width: 100%;">
	</p>

	<table>
	<thead>
	<tr>
	<th rowspan="2">类型</th>
	<th rowspan="2" width="160">方法</th>
	<th colspan="3">S&P 500</th>
	<th colspan="3">CSI 300</th>
	</tr>
	<tr>
	<th>AR (%)</th>
	<th>SR</th>
	<th>MDD (%)</th>
	<th>AR (%)</th>
	<th>SR</th>
	<th>MDD (%)</th>
	</tr>
	</thead>
	<tbody>
	<tr><td rowspan="9">Non-LLM</td><td>Buy & Hold</td><td>19.34</td><td>0.80</td><td>18.75</td><td>22.16</td><td>1.31</td><td>10.49</td></tr>
	<tr><td>PCA</td><td>7.98</td><td>0.27</td><td>17.30</td><td>2.93</td><td>0.17</td><td>14.46</td></tr>
	<tr><td>XGBoost</td><td>3.49</td><td>0.03</td><td>18.45</td><td>8.99</td><td>0.50</td><td>16.26</td></tr>
	<tr><td>LightGBM</td><td>-5.42</td><td>-0.43</td><td>20.93</td><td>18.44</td><td>1.05</td><td>14.92</td></tr>
	<tr><td>A2C</td><td>10.82</td><td>0.40</td><td>17.70</td><td>22.96</td><td>1.20</td><td>14.86</td></tr>
	<tr><td>PPO</td><td>7.68</td><td>0.25</td><td>14.97</td><td>14.96</td><td>0.81</td><td>12.95</td></tr>
	<tr><td>DDPG</td><td>2.53</td><td>-0.02</td><td>15.04</td><td>1.97</td><td>0.12</td><td>16.54</td></tr>
	<tr><td>TD3</td><td>5.54</td><td>0.14</td><td>16.58</td><td>8.66</td><td>0.52</td><td>10.26</td></tr>
	<tr><td>SAC</td><td>37.60</td><td>1.44</td><td>15.18</td><td>9.77</td><td>0.56</td><td>11.68</td></tr>
	<tr><td rowspan="5">LLM</td><td>Gemini 2.5 Pro</td><td>14.23</td><td>0.55</td><td>17.01</td><td>16.29</td><td>0.90</td><td>14.01</td></tr>
	<tr><td>Claude 3.7 Sonnet</td><td>10.92</td><td>0.40</td><td>18.88</td><td>10.13</td><td>0.57</td><td>14.49</td></tr>
	<tr><td>DeepSeek‑R1</td><td>21.94</td><td>0.93</td><td><b>14.36</b></td><td>14.66</td><td>0.81</td><td>14.60</td></tr>
	<tr><td>Qwen3‑8B</td><td>12.85</td><td>0.47</td><td>19.52</td><td>15.44</td><td>0.79</td><td>14.38</td></tr>
	<tr><td><b>Alpha‑R1 (Ours)</b></td><td><b>47.87</b></td><td><b>1.62</b></td><td>16.91</td><td><b>40.57</b></td><td><b>2.23</b></td><td><b>6.58</b></td></tr>
	</tbody>
	</table>

	域外泛化（无需重训，论文 Table 2）：Russell 2000 上 80.54% AR（SR 2.46），CSI 1000 上 73.52% AR（SR 2.80）。AR = 年化收益，SR = 超额夏普比率，MDD = 最大回撤。

	## 训练 (Training)

	基于 Qwen3-8B，使用 verl 进行 GRPO 训练，奖励为市场反馈奖励（`R_final = R_adjusted - P_structural`，论文 §3.4）。训练配置与参考奖励实现见 GitHub 仓库的 `training/` 目录。

	## 局限性 (Limitations)

	- 本模型面向学术研究场景，输出不构成任何投资建议。
	- 因子筛选依赖上游的描述生成与回测管线（见 GitHub 仓库），模型本身不直接产出可交易信号。

	## 引用 (Citation)

	```bibtex
	@article{jiang2025alphar1,
	title={Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning},
	author={Jiang, Zuoyou and Zhao, Li and Sun, Rui and Sun, Ruohan and Li, Zhongjian and Li, Jing and Jiang, Daxin and Bai, Zuo and Hua, Cheng},
	journal={arXiv preprint arXiv:2512.23515},
	year={2025}
	}
	```

	## License

	本项目基于 [MIT License](https://opensource.org/licenses/MIT) 发布。