Instructions to use May2222/Fisher-R1-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use May2222/Fisher-R1-14B with Transformers:

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

pipe = pipeline("text-generation", model="May2222/Fisher-R1-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("May2222/Fisher-R1-14B")
model = AutoModelForCausalLM.from_pretrained("May2222/Fisher-R1-14B", 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 May2222/Fisher-R1-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "May2222/Fisher-R1-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "May2222/Fisher-R1-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/May2222/Fisher-R1-14B

SGLang

How to use May2222/Fisher-R1-14B 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 "May2222/Fisher-R1-14B" \
    --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": "May2222/Fisher-R1-14B",
		"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 "May2222/Fisher-R1-14B" \
        --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": "May2222/Fisher-R1-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use May2222/Fisher-R1-14B with Docker Model Runner:
```
docker model run hf.co/May2222/Fisher-R1-14B
```

Fisher-R1-14B / README.md

May2222

Release Fisher-R1-14B

70f06f5 2 days ago

preview code

Raw

History Blame Contribute Delete

1.5 kB

	---
	library_name: transformers
	license: apache-2.0
	pipeline_tag: text-generation
	base_model: Qwen/Qwen2.5-Coder-14B-Instruct
	datasets:
	- May2222/P-Bench
	language:
	- en
	tags:
	- statistics
	- hypothesis-testing
	- tool-use
	---

	# Fisher-R1-14B

	Fisher-R1-14B is an open-weight LLM agent for reliable hypothesis testing. It is post-trained from Qwen2.5-Coder-14B-Instruct on synthetic executable statistical tasks, using supervised fine-tuning followed by reinforcement learning with verified statistical rewards.

	The model is designed to inspect data, select and execute an appropriate statistical test, report a p-value, and draw a conclusion. It is evaluated on [P-Bench](https://huggingface.co/datasets/May2222/P-Bench).

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_id = "May2222/Fisher-R1-14B"
	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(
	model_id,
	torch_dtype="auto",
	device_map="auto",
	)
	```

	For the training setup, evaluation protocol, and results, see [Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing](https://arxiv.org/abs/2608.07437).

	## Citation

	```bibtex
	@article{miao2026fisherr1,
	title = {Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing},
	author = {Miao, Jiacheng and Mu, Jin and Chen, Guanhua and Zou, James},
	journal = {arXiv preprint arXiv:2608.07437},
	year = {2026},
	url = {https://arxiv.org/abs/2608.07437}
	}
	```