Instructions to use utkarshkingh/llama_3.2-vision_instruct_bpmncoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use utkarshkingh/llama_3.2-vision_instruct_bpmncoder with Transformers:

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

pipe = pipeline("image-text-to-text", model="utkarshkingh/llama_3.2-vision_instruct_bpmncoder")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("utkarshkingh/llama_3.2-vision_instruct_bpmncoder")
model = AutoModelForMultimodalLM.from_pretrained("utkarshkingh/llama_3.2-vision_instruct_bpmncoder", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use utkarshkingh/llama_3.2-vision_instruct_bpmncoder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "utkarshkingh/llama_3.2-vision_instruct_bpmncoder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "utkarshkingh/llama_3.2-vision_instruct_bpmncoder",
		"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/utkarshkingh/llama_3.2-vision_instruct_bpmncoder

SGLang

How to use utkarshkingh/llama_3.2-vision_instruct_bpmncoder 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 "utkarshkingh/llama_3.2-vision_instruct_bpmncoder" \
    --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": "utkarshkingh/llama_3.2-vision_instruct_bpmncoder",
		"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 "utkarshkingh/llama_3.2-vision_instruct_bpmncoder" \
        --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": "utkarshkingh/llama_3.2-vision_instruct_bpmncoder",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use utkarshkingh/llama_3.2-vision_instruct_bpmncoder with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for utkarshkingh/llama_3.2-vision_instruct_bpmncoder to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for utkarshkingh/llama_3.2-vision_instruct_bpmncoder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for utkarshkingh/llama_3.2-vision_instruct_bpmncoder to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="utkarshkingh/llama_3.2-vision_instruct_bpmncoder",
    max_seq_length=2048,
)

Docker Model Runner
How to use utkarshkingh/llama_3.2-vision_instruct_bpmncoder with Docker Model Runner:
```
docker model run hf.co/utkarshkingh/llama_3.2-vision_instruct_bpmncoder
```

utkarshkingh commited on Mar 23, 2025

Commit

58c131f

verified ·

1 Parent(s): 6ab872a

(Trained with Unsloth)

Browse files

Files changed (2) hide show

config.json +109 -0
generation_config.json +13 -0

config.json ADDED Viewed

	@@ -0,0 +1,109 @@

+{
+    "architectures": [
+        "MllamaForConditionalGeneration"
+    ],
+    "image_token_index": 128256,
+    "model_type": "mllama",
+    "pad_token_id": 128004,
+    "text_config": {
+        "cross_attention_layers": [
+            3,
+            8,
+            13,
+            18,
+            23,
+            28,
+            33,
+            38
+        ],
+        "dropout": 0,
+        "eos_token_id": [
+            128001,
+            128008,
+            128009
+        ],
+        "hidden_act": "silu",
+        "hidden_size": 4096,
+        "initializer_range": 0.02,
+        "intermediate_size": 14336,
+        "max_position_embeddings": 131072,
+        "model_type": "mllama_text_model",
+        "num_attention_heads": 32,
+        "num_hidden_layers": 40,
+        "num_key_value_heads": 8,
+        "rms_norm_eps": 1e-05,
+        "rope_scaling": {
+            "factor": 8.0,
+            "high_freq_factor": 4.0,
+            "low_freq_factor": 1.0,
+            "original_max_position_embeddings": 8192,
+            "rope_type": "llama3"
+        },
+        "rope_theta": 500000.0,
+        "torch_dtype": "bfloat16",
+        "use_cache": true,
+        "vocab_size": 128256
+    },
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.50.0",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.3.18",
+    "vision_config": {
+        "attention_heads": 16,
+        "hidden_act": "gelu",
+        "hidden_size": 1280,
+        "image_size": 560,
+        "initializer_range": 0.02,
+        "intermediate_layers_indices": [
+            3,
+            7,
+            15,
+            23,
+            30
+        ],
+        "intermediate_size": 5120,
+        "max_num_tiles": 4,
+        "model_type": "mllama_vision_model",
+        "norm_eps": 1e-05,
+        "num_channels": 3,
+        "num_global_layers": 8,
+        "num_hidden_layers": 32,
+        "patch_size": 14,
+        "supported_aspect_ratios": [
+            [
+                1,
+                1
+            ],
+            [
+                1,
+                2
+            ],
+            [
+                1,
+                3
+            ],
+            [
+                1,
+                4
+            ],
+            [
+                2,
+                1
+            ],
+            [
+                2,
+                2
+            ],
+            [
+                3,
+                1
+            ],
+            [
+                4,
+                1
+            ]
+        ],
+        "torch_dtype": "bfloat16",
+        "vision_output_dim": 7680
+    }
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.50.0"
+}