Instructions to use arianraje/mimo-7b-gdn-hybrid-2.0B-OPD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arianraje/mimo-7b-gdn-hybrid-2.0B-OPD with Transformers:

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

pipe = pipeline("text-generation", model="arianraje/mimo-7b-gdn-hybrid-2.0B-OPD")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("arianraje/mimo-7b-gdn-hybrid-2.0B-OPD", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arianraje/mimo-7b-gdn-hybrid-2.0B-OPD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arianraje/mimo-7b-gdn-hybrid-2.0B-OPD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arianraje/mimo-7b-gdn-hybrid-2.0B-OPD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arianraje/mimo-7b-gdn-hybrid-2.0B-OPD

SGLang

How to use arianraje/mimo-7b-gdn-hybrid-2.0B-OPD 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 "arianraje/mimo-7b-gdn-hybrid-2.0B-OPD" \
    --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": "arianraje/mimo-7b-gdn-hybrid-2.0B-OPD",
		"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 "arianraje/mimo-7b-gdn-hybrid-2.0B-OPD" \
        --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": "arianraje/mimo-7b-gdn-hybrid-2.0B-OPD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arianraje/mimo-7b-gdn-hybrid-2.0B-OPD with Docker Model Runner:
```
docker model run hf.co/arianraje/mimo-7b-gdn-hybrid-2.0B-OPD
```

mimo-7b-gdn-hybrid-2.0B-OPD / surgery_report.json

arianraje

stage3-2.0B-OPD decayed final (H=32K, matched 1.8B recipe; run mimo-mathmix-h32k-runpod-2p0b-v1-20260905)

36767e6 verified 19 days ago

Raw

History Blame Contribute Delete

777 Bytes

	{
	"total_params": 8309898304,
	"inherited_params": 8301930496,
	"inherited_fraction": 0.9990411666053525,
	"dropped_teacher_bias_params": 165888,
	"teacher": "/ocean/projects/cis250011p/araje1/cache/hf_cache/hub/models--XiaomiMiMo--MiMo-7B-RL-0530/snapshots/323400599af3903adc2a536d6340a23fee88d2e0",
	"teacher_family": "mimo",
	"teacher_unexpected_keys_ignored": 16,
	"teacher_params": 7622619136,
	"full_attention_layers": [
	3,
	7,
	11,
	15,
	19,
	23,
	27,
	31,
	35
	],
	"surgery": {
	"full_attention_layers": null,
	"interval": 4,
	"linear_num_key_heads": 16,
	"linear_num_value_heads": 32,
	"linear_key_head_dim": 128,
	"linear_value_head_dim": 128,
	"linear_conv_kernel_dim": 4,
	"conv_init": "default"
	}
	}