Instructions to use TheGarageDev/Minus-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheGarageDev/Minus-v0.2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="TheGarageDev/Minus-v0.2")
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("TheGarageDev/Minus-v0.2")
model = AutoModelForMultimodalLM.from_pretrained("TheGarageDev/Minus-v0.2", 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 TheGarageDev/Minus-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheGarageDev/Minus-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheGarageDev/Minus-v0.2",
		"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/TheGarageDev/Minus-v0.2

SGLang

How to use TheGarageDev/Minus-v0.2 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 "TheGarageDev/Minus-v0.2" \
    --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": "TheGarageDev/Minus-v0.2",
		"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 "TheGarageDev/Minus-v0.2" \
        --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": "TheGarageDev/Minus-v0.2",
		"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 TheGarageDev/Minus-v0.2 with Docker Model Runner:
```
docker model run hf.co/TheGarageDev/Minus-v0.2
```

Minus-v0.2 / conversion /example_config_attn_layer.json

GarageCyril

Minus-v0.2: squash-trained LFM2.5-VL-450M + screen-state head, AX650 build with FP32 residual stream

97d19f2 verified 9 days ago

Raw History Blame Contribute Delete

2.1 kB

{
 "model_type": "ONNX",
 "npu_mode": "NPU3",
 "target_hardware": "AX650",
 "onnx_opt": {
  "enable_onnxsim": false
 },
 "quant": {
  "input_configs": [
   {
    "tensor_name": "hidden",
    "calibration_dataset": "/data/calib/l2_attn_fused/hidden.tar",
    "calibration_format": "Numpy",
    "calibration_size": -1
   },
   {
    "tensor_name": "mask",
    "calibration_dataset": "/data/calib/l2_attn_fused/mask.tar",
    "calibration_format": "Numpy",
    "calibration_size": -1
   },
   {
    "tensor_name": "indices",
    "calibration_dataset": "/data/calib/l2_attn_fused/indices.tar",
    "calibration_format": "Numpy",
    "calibration_size": -1
   }
  ],
  "layer_configs": [
   {
    "start_tensor_names": [
     "DEFAULT"
    ],
    "end_tensor_names": [
     "DEFAULT"
    ],
    "data_type": "U16"
   },
   {
    "layer_names": [
     "/operator_norm/Mul",
     "/operator_norm/ReduceMean",
     "/operator_norm/Add",
     "/operator_norm/Sqrt",
     "/operator_norm/Div",
     "/operator_norm/Mul_1",
     "/self_attn/q_layernorm/Mul",
     "/self_attn/q_layernorm/ReduceMean",
     "/self_attn/q_layernorm/Add",
     "/self_attn/q_layernorm/Sqrt",
     "/self_attn/q_layernorm/Div",
     "/self_attn/q_layernorm/Mul_1",
     "/self_attn/k_layernorm/Mul",
     "/self_attn/k_layernorm/ReduceMean",
     "/self_attn/k_layernorm/Add",
     "/self_attn/k_layernorm/Sqrt",
     "/self_attn/k_layernorm/Div",
     "/self_attn/k_layernorm/Mul_1",
     "/ffn_norm/Mul",
     "/ffn_norm/ReduceMean",
     "/ffn_norm/Add",
     "/ffn_norm/Sqrt",
     "/ffn_norm/Div",
     "/ffn_norm/Mul_1",
     "/Add",
     "/Add_1",
     "/self_attn/Add_2"
    ],
    "data_type": "FP32"
   }
  ],
  "calibration_method": "MinMax",
  "precision_analysis": true,
  "precision_analysis_method": "EndToEnd",
  "conv_bias_data_type": "FP32",
  "enable_smooth_quant": false
 },
 "input_processors": [
  {
   "tensor_name": "hidden",
   "src_dtype": "FP32"
  },
  {
   "tensor_name": "mask",
   "src_dtype": "FP32"
  },
  {
   "tensor_name": "indices",
   "src_dtype": "S32"
  }
 ],
 "compiler": {
  "check": 0
 }
}

	{
	"model_type": "ONNX",
	"npu_mode": "NPU3",
	"target_hardware": "AX650",
	"onnx_opt": {
	"enable_onnxsim": false
	},
	"quant": {
	"input_configs": [
	{
	"tensor_name": "hidden",
	"calibration_dataset": "/data/calib/l2_attn_fused/hidden.tar",
	"calibration_format": "Numpy",
	"calibration_size": -1
	},
	{
	"tensor_name": "mask",
	"calibration_dataset": "/data/calib/l2_attn_fused/mask.tar",
	"calibration_format": "Numpy",
	"calibration_size": -1
	},
	{
	"tensor_name": "indices",
	"calibration_dataset": "/data/calib/l2_attn_fused/indices.tar",
	"calibration_format": "Numpy",
	"calibration_size": -1
	}
	],
	"layer_configs": [
	{
	"start_tensor_names": [
	"DEFAULT"
	],
	"end_tensor_names": [
	"DEFAULT"
	],
	"data_type": "U16"
	},
	{
	"layer_names": [
	"/operator_norm/Mul",
	"/operator_norm/ReduceMean",
	"/operator_norm/Add",
	"/operator_norm/Sqrt",
	"/operator_norm/Div",
	"/operator_norm/Mul_1",
	"/self_attn/q_layernorm/Mul",
	"/self_attn/q_layernorm/ReduceMean",
	"/self_attn/q_layernorm/Add",
	"/self_attn/q_layernorm/Sqrt",
	"/self_attn/q_layernorm/Div",
	"/self_attn/q_layernorm/Mul_1",
	"/self_attn/k_layernorm/Mul",
	"/self_attn/k_layernorm/ReduceMean",
	"/self_attn/k_layernorm/Add",
	"/self_attn/k_layernorm/Sqrt",
	"/self_attn/k_layernorm/Div",
	"/self_attn/k_layernorm/Mul_1",
	"/ffn_norm/Mul",
	"/ffn_norm/ReduceMean",
	"/ffn_norm/Add",
	"/ffn_norm/Sqrt",
	"/ffn_norm/Div",
	"/ffn_norm/Mul_1",
	"/Add",
	"/Add_1",
	"/self_attn/Add_2"
	],
	"data_type": "FP32"
	}
	],
	"calibration_method": "MinMax",
	"precision_analysis": true,
	"precision_analysis_method": "EndToEnd",
	"conv_bias_data_type": "FP32",
	"enable_smooth_quant": false
	},
	"input_processors": [
	{
	"tensor_name": "hidden",
	"src_dtype": "FP32"
	},
	{
	"tensor_name": "mask",
	"src_dtype": "FP32"
	},
	{
	"tensor_name": "indices",
	"src_dtype": "S32"
	}
	],
	"compiler": {
	"check": 0
	}
	}