Instructions to use arcadianlee/Raven-reasoning-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcadianlee/Raven-reasoning-1.0 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-32b-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "arcadianlee/Raven-reasoning-1.0")

Transformers

How to use arcadianlee/Raven-reasoning-1.0 with Transformers:

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

pipe = pipeline("text-generation", model="arcadianlee/Raven-reasoning-1.0")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("arcadianlee/Raven-reasoning-1.0", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arcadianlee/Raven-reasoning-1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcadianlee/Raven-reasoning-1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcadianlee/Raven-reasoning-1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/arcadianlee/Raven-reasoning-1.0

SGLang

How to use arcadianlee/Raven-reasoning-1.0 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 "arcadianlee/Raven-reasoning-1.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcadianlee/Raven-reasoning-1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "arcadianlee/Raven-reasoning-1.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcadianlee/Raven-reasoning-1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use arcadianlee/Raven-reasoning-1.0 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for arcadianlee/Raven-reasoning-1.0 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for arcadianlee/Raven-reasoning-1.0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for arcadianlee/Raven-reasoning-1.0 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="arcadianlee/Raven-reasoning-1.0",
    max_seq_length=2048,
)

Docker Model Runner
How to use arcadianlee/Raven-reasoning-1.0 with Docker Model Runner:
```
docker model run hf.co/arcadianlee/Raven-reasoning-1.0
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card for Raven-reasoning

LLM-orchetrasted agents for the autonomous discovery of novel materials with agentic reasoning. This LLM model is a fine-tuned version of unsloth/qwen2.5-32b-bnb-4bit and post-trained wit GRPO.

Model Details

Model Description

Developed by: Renjie Li
Funded by [optional]: IIDAI, IBM
Shared by [optional]: [More Information Needed]
Model type: LoRA
Language(s) (NLP): English
License: Apache 2.0
Finetuned from model [optional]: Qwen2.5-32B-Instruct

Model Sources [optional]

Repository: https://github.com/AnonymousUser-3/QuantumChem-200K
Paper [optional]: https://arxiv.org/pdf/2511.21747
Demo [optional]: https://ravenllm.com

Quick start

from transformers import pipeline

question = "You are Raven's inverse polymer design model.\nGiven target material properties, reason about the molecular features needed,\nthen propose one chemically plausible candidate."
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with GRPO on the QuantumChem-200k dataset, a method introduced in DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Framework versions

PEFT 0.19.1
TRL: 0.23.0
Transformers: 4.57.1
Pytorch: 2.6.0
Datasets: 4.3.0
Tokenizers: 0.22.1

Citations

Cite GRPO as:

@article{shao2024deepseekmath,
    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
    year         = 2024,
    eprint       = {arXiv:2402.03300},
}

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: -

Dataset used to train arcadianlee/Raven-reasoning-1.0

Papers for arcadianlee/Raven-reasoning-1.0

QuantumChem-200K: A Large-Scale Open Organic Molecular Dataset for Quantum-Chemistry Property Screening and Language Model Benchmarking

Paper • 2511.21747 • Published Nov 23, 2025

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Paper • 2402.03300 • Published Feb 5, 2024 • 148