Instructions to use codercat/AtmosRegime-Qwen3.5-9B-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codercat/AtmosRegime-Qwen3.5-9B-RL with Transformers:

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

pipe = pipeline("text-generation", model="codercat/AtmosRegime-Qwen3.5-9B-RL")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("codercat/AtmosRegime-Qwen3.5-9B-RL")
model = AutoModelForMultimodalLM.from_pretrained("codercat/AtmosRegime-Qwen3.5-9B-RL", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use codercat/AtmosRegime-Qwen3.5-9B-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codercat/AtmosRegime-Qwen3.5-9B-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codercat/AtmosRegime-Qwen3.5-9B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/codercat/AtmosRegime-Qwen3.5-9B-RL

SGLang

How to use codercat/AtmosRegime-Qwen3.5-9B-RL 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 "codercat/AtmosRegime-Qwen3.5-9B-RL" \
    --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": "codercat/AtmosRegime-Qwen3.5-9B-RL",
		"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 "codercat/AtmosRegime-Qwen3.5-9B-RL" \
        --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": "codercat/AtmosRegime-Qwen3.5-9B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use codercat/AtmosRegime-Qwen3.5-9B-RL with Docker Model Runner:
```
docker model run hf.co/codercat/AtmosRegime-Qwen3.5-9B-RL
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

AtmosRegime-Qwen3.5-9B-RL

Qwen3.5-9B trained with reinforcement learning with verifiable rewards on atmospheric and environmental calculations, from the paper Language models misapply atmospheric formulas until trained on a few worked examples. In the paper, this training lets Qwen3.5-9B match DeepSeek V4 Flash on benchmark regime problems, both without thinking.

Code and data: https://github.com/acodercat/AtmosRegime. The other models from the paper are in the AtmosRegime collection.

Training

Base model: Qwen3.5-9B, thinking off.
Method: DAPO in verl. The reward is 1 when the program the model writes runs and returns the certified answer, otherwise 0.
Data: problems generated from the templates of training fold 1 (29 of the 70 mechanisms, split by cluster), each in its inside, outside and given versions.
Settings: learning rate 1e-6, 128 problems × 8 samples per step, up to 120 steps; seed 42.

Use

The model was trained on one prompt format and should be given the same one. It answers with a Python program that defines solve(). Run it with thinking disabled.

Load the model as you would its base model, Qwen/Qwen3.5-9B, and build the messages with atmoscoder_rl.prompts.chat(problem) from the code repository (a fixed system prompt and a user template that asks for solve()). Execution and grading of the returned program are in atmoscoder_rl/evaluation/.

Limitations

This checkpoint is one fold and one seed. Numbers in the paper average both folds and two seeds, so this model alone will not reproduce them exactly.
Reinforcement learning alone rarely taught the model a formula its base model almost never produced. Where training did not repair a mechanism, the model may still return the standard formula's value.
It was trained and tested on problems from the study's templates and benchmark. It is not a general-purpose assistant for atmospheric science.

Citation

@unpublished{ran2026regime,
  title  = {Language models misapply atmospheric formulas until trained on a few worked examples},
  author = {Ran, Maohao and Zhang, Yanting and Ma, Chendong and Song, Jun},
  year   = {2026},
  note   = {Manuscript under review}
}