Instructions to use omida-ai/omida-r2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use omida-ai/omida-r2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="omida-ai/omida-r2")
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("omida-ai/omida-r2")
model = AutoModelForMultimodalLM.from_pretrained("omida-ai/omida-r2", 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 omida-ai/omida-r2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "omida-ai/omida-r2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "omida-ai/omida-r2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/omida-ai/omida-r2

SGLang

How to use omida-ai/omida-r2 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 "omida-ai/omida-r2" \
    --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": "omida-ai/omida-r2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "omida-ai/omida-r2" \
        --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": "omida-ai/omida-r2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use omida-ai/omida-r2 with Docker Model Runner:
```
docker model run hf.co/omida-ai/omida-r2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Omida R2 Research Candidate

Omida R2 is a post-trained research artifact built from Qwen/Qwen3.5-9B at commit c202236235762e1c871ad0ccb60c8ee5ba337b9a. It is not trained from scratch. The base checkpoint's Apache-2.0 license is included in this directory; source datasets retain their upstream licenses and attribution in data/r2/provenance.jsonl.

Method

Text-only NF4 QLoRA supervised fine-tuning (r2-sft-001) followed by two TRL GRPO passes (r2-grpo-001, r2-grpo-002) using procedurally generated arithmetic prompts and an exact-integer reward. The merged weights are BF16 safetensors; the tested local runtime loads them with NF4 double quantization and BF16 compute.

Small local evaluation (not broad superiority)

Suite	Untouched Qwen3.5-9B	Omida R1 merged	Omida R2 merged
Omida Operator Eval, 30 tasks	29/30	29/30	27/30
Fixed GSM8K test subset, 30 tasks	20/30	22/30	27/30
Held-out xLAM exact JSON calls, 100 tasks	68/100	67/100	79/100
Generated exact arithmetic, 64 tasks	59/64	not run	51/64

R2 shows promising gains over the base model on the measured GSM8K subset and held-out exact JSON tool-call set. The tool-call evaluation measures serialization and argument correctness, rather than runtime tool execution. These evaluations are small and task-specific: operator completion and generated arithmetic scores are lower than the base model, and broader coding, agentic, and hallucination-rate improvements have not yet been established.

Local use

From the repository root, use the included NF4 inference config:

.venv\Scripts\python.exe inference\run_omida.py --config inference\r2_config.json

Training configs, adapters, checkpoints, evaluation outputs, and reproducibility logs are retained in the repository under configs/, runs/, and eval/omida-r2/. See reports/FINAL_REPORT.md for complete lineage and limitations.

Downloads last month: 34

Safetensors

Model size

10B params

Tensor type

BF16

F32

Model tree for omida-ai/omida-r2

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(1229)

this model

Quantizations

1 model