Instructions to use omicverse/OmicAI-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use omicverse/OmicAI-9B with Transformers:

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

pipe = pipeline("text-generation", model="omicverse/OmicAI-9B")
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("omicverse/OmicAI-9B")
model = AutoModelForMultimodalLM.from_pretrained("omicverse/OmicAI-9B", 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 omicverse/OmicAI-9B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/omicverse/OmicAI-9B

SGLang

How to use omicverse/OmicAI-9B 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 "omicverse/OmicAI-9B" \
    --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": "omicverse/OmicAI-9B",
		"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 "omicverse/OmicAI-9B" \
        --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": "omicverse/OmicAI-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use omicverse/OmicAI-9B with Docker Model Runner:
```
docker model run hf.co/omicverse/OmicAI-9B
```

OmicAI-9B / README.md

starlitnightly

Add OmicAI family table

dc03f83 verified 28 days ago

preview code

Raw History Blame Contribute Delete

2.28 kB

---
license: apache-2.0
base_model: XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
library_name: transformers
pipeline_tag: text-generation
language: [en]
tags: [omics, bioinformatics, single-cell, spatial-transcriptomics, omicverse, agent, tool-calling, scientific-coding]
---
# OmicAI-9B

The **9B** member of **OmicAI**, a family optimized for **omics data analysis and
tool interaction** over [omicverse](https://github.com/omicverse/omicverse).
Fine-tuned with **ms-swift LoRA (all-linear, r16, α32) merged** on a
Qwen3.5-9B-architecture base (MiMo-V2.6-Distill-Qwen-9B).

## The OmicAI family

| Model | Base | Access |
|---|---|---|
| [OmicAI-0.8B](https://huggingface.co/omicverse/OmicAI-0.8B) | Qwen3.5-0.8B | Open — Apache-2.0 |
| [OmicAI-4B](https://huggingface.co/omicverse/OmicAI-4B) | Qwen3.5-4B | Open — Apache-2.0 |
| **OmicAI-9B** *(this model)* | MiMo-V2.6-Distill-Qwen-9B | Open — Apache-2.0 |
| [OmicAI-27B](https://huggingface.co/omicverse/OmicAI-27B) | Qwen3.8-27B | By application |

## Training Data
Trajectories produced by **OmicOS** and **OmicVerse** through a **paper-reproduction
process over the last three years of publications** (retrieve recent omics papers →
reproduce their analyses end-to-end → multi-turn agent trajectories of retrieval,
code, **omicverse** tool calls, execution-feedback recovery). Kept only when a
**judge** confirms legitimacy **and** a **scoreboard** confirms the result
**matches or surpasses** the paper's reported (SOTA) numbers.

## Key Details
| | |
|---|---|
| **Base model** | XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B (Qwen3.5-9B architecture) |
| **Method** | ms-swift LoRA (all-linear, r16, α32) → merged |
| **Chat template** | `qwen3_5` — *inference template must match training* |
| **Precision** | bfloat16 (4 shards) |

## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("omicverse/OmicAI-9B")
model = AutoModelForCausalLM.from_pretrained("omicverse/OmicAI-9B", torch_dtype="bfloat16", device_map="auto")
```

## Ecosystem
Part of **omicOS / omicAI**. Siblings: [OmicAI-4B](https://huggingface.co/omicverse/OmicAI-4B) · [OmicAI-27B](https://huggingface.co/omicverse/OmicAI-27B) · [OmicAI-0.8B](https://huggingface.co/omicverse/OmicAI-0.8B).

	---
	license: apache-2.0
	base_model: XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
	library_name: transformers
	pipeline_tag: text-generation
	language: [en]
	tags: [omics, bioinformatics, single-cell, spatial-transcriptomics, omicverse, agent, tool-calling, scientific-coding]
	---

	# OmicAI-9B

	The 9B member of OmicAI, a family optimized for **omics data analysis and
	tool interaction** over [omicverse](https://github.com/omicverse/omicverse).
	Fine-tuned with ms-swift LoRA (all-linear, r16, α32) merged on a
	Qwen3.5-9B-architecture base (MiMo-V2.6-Distill-Qwen-9B).

	## The OmicAI family

	\| Model \| Base \| Access \|
	\|---\|---\|---\|
	\| [OmicAI-0.8B](https://huggingface.co/omicverse/OmicAI-0.8B) \| Qwen3.5-0.8B \| Open — Apache-2.0 \|
	\| [OmicAI-4B](https://huggingface.co/omicverse/OmicAI-4B) \| Qwen3.5-4B \| Open — Apache-2.0 \|
	\| OmicAI-9B (this model) \| MiMo-V2.6-Distill-Qwen-9B \| Open — Apache-2.0 \|
	\| [OmicAI-27B](https://huggingface.co/omicverse/OmicAI-27B) \| Qwen3.8-27B \| By application \|

	## Training Data
	Trajectories produced by OmicOS and OmicVerse through a **paper-reproduction
	process over the last three years of publications** (retrieve recent omics papers →
	reproduce their analyses end-to-end → multi-turn agent trajectories of retrieval,
	code, omicverse tool calls, execution-feedback recovery). Kept only when a
	judge confirms legitimacy and a scoreboard confirms the result
	matches or surpasses the paper's reported (SOTA) numbers.

	## Key Details
	\| \| \|
	\|---\|---\|
	\| Base model \| XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B (Qwen3.5-9B architecture) \|
	\| Method \| ms-swift LoRA (all-linear, r16, α32) → merged \|
	\| Chat template \| `qwen3_5` — inference template must match training \|
	\| Precision \| bfloat16 (4 shards) \|

	## Usage
	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	tok = AutoTokenizer.from_pretrained("omicverse/OmicAI-9B")
	model = AutoModelForCausalLM.from_pretrained("omicverse/OmicAI-9B", torch_dtype="bfloat16", device_map="auto")
	```

	## Ecosystem
	Part of omicOS / omicAI. Siblings: [OmicAI-4B](https://huggingface.co/omicverse/OmicAI-4B) · [OmicAI-27B](https://huggingface.co/omicverse/OmicAI-27B) · [OmicAI-0.8B](https://huggingface.co/omicverse/OmicAI-0.8B).