Instructions to use NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum with Transformers:

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

pipe = pipeline("image-text-to-text", model="NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum")
model = AutoModelForImageTextToText.from_pretrained("NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum")
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 NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum",
		"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/NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum

SGLang

How to use NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum 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 "NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum" \
    --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": "NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum",
		"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 "NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum" \
        --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": "NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum",
		"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 NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum 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 NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum 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 NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum",
    max_seq_length=2048,
)

Docker Model Runner
How to use NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum with Docker Model Runner:
```
docker model run hf.co/NTA1802/Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum
```

Qwen2VL_2B_Instruct_Tuning_ViReceipt_Sum / config.json

NTA1802

(Trained with Unsloth)

e87002a verified 9 months ago

raw

history blame contribute delete

11.2 kB

	{
	"architectures": [
	"Qwen2VLForConditionalGeneration"
	],
	"attention_dropout": 0.0,
	"dtype": "float16",
	"eos_token_id": 151645,
	"hidden_act": "silu",
	"hidden_size": 1536,
	"image_token_id": 151655,
	"initializer_range": 0.02,
	"intermediate_size": 8960,
	"max_position_embeddings": 32768,
	"max_window_layers": 28,
	"model_type": "qwen2_vl",
	"num_attention_heads": 12,
	"num_hidden_layers": 28,
	"num_key_value_heads": 2,
	"pad_token_id": 151654,
	"quantization_config": {
	"bnb_4bit_compute_dtype": "float16",
	"bnb_4bit_quant_type": "nf4",
	"bnb_4bit_use_double_quant": true,
	"llm_int8_enable_fp32_cpu_offload": false,
	"llm_int8_has_fp16_weight": false,
	"llm_int8_skip_modules": [
	"model.visual.blocks.0.attn.qkv",
	"model.visual.blocks.0.attn.proj",
	"model.visual.blocks.0.mlp.fc1",
	"model.visual.blocks.0.mlp.fc2",
	"model.visual.blocks.1.attn.qkv",
	"model.visual.blocks.1.attn.proj",
	"model.visual.blocks.1.mlp.fc1",
	"model.visual.blocks.1.mlp.fc2",
	"model.visual.blocks.2.attn.qkv",
	"model.visual.blocks.2.attn.proj",
	"model.visual.blocks.2.mlp.fc1",
	"model.visual.blocks.2.mlp.fc2",
	"model.visual.blocks.3.attn.qkv",
	"model.visual.blocks.3.attn.proj",
	"model.visual.blocks.3.mlp.fc1",
	"model.visual.blocks.3.mlp.fc2",
	"model.visual.blocks.4.attn.qkv",
	"model.visual.blocks.4.attn.proj",
	"model.visual.blocks.4.mlp.fc1",
	"model.visual.blocks.4.mlp.fc2",
	"model.visual.blocks.5.attn.qkv",
	"model.visual.blocks.5.attn.proj",
	"model.visual.blocks.5.mlp.fc1",
	"model.visual.blocks.5.mlp.fc2",
	"model.visual.blocks.6.attn.qkv",
	"model.visual.blocks.6.attn.proj",
	"model.visual.blocks.6.mlp.fc1",
	"model.visual.blocks.6.mlp.fc2",
	"model.visual.blocks.7.attn.qkv",
	"model.visual.blocks.7.attn.proj",
	"model.visual.blocks.7.mlp.fc1",
	"model.visual.blocks.7.mlp.fc2",
	"model.visual.blocks.8.attn.qkv",
	"model.visual.blocks.8.attn.proj",
	"model.visual.blocks.8.mlp.fc1",
	"model.visual.blocks.8.mlp.fc2",
	"model.visual.blocks.9.attn.qkv",
	"model.visual.blocks.9.attn.proj",
	"model.visual.blocks.9.mlp.fc1",
	"model.visual.blocks.9.mlp.fc2",
	"model.visual.blocks.10.attn.qkv",
	"model.visual.blocks.10.attn.proj",
	"model.visual.blocks.10.mlp.fc1",
	"model.visual.blocks.10.mlp.fc2",
	"model.visual.blocks.11.attn.qkv",
	"model.visual.blocks.11.attn.proj",
	"model.visual.blocks.11.mlp.fc1",
	"model.visual.blocks.11.mlp.fc2",
	"model.visual.blocks.12.attn.qkv",
	"model.visual.blocks.12.attn.proj",
	"model.visual.blocks.12.mlp.fc1",
	"model.visual.blocks.12.mlp.fc2",
	"model.visual.blocks.13.attn.qkv",
	"model.visual.blocks.13.attn.proj",
	"model.visual.blocks.13.mlp.fc1",
	"model.visual.blocks.13.mlp.fc2",
	"model.visual.blocks.14.attn.qkv",
	"model.visual.blocks.14.attn.proj",
	"model.visual.blocks.14.mlp.fc1",
	"model.visual.blocks.14.mlp.fc2",
	"model.visual.blocks.15.attn.qkv",
	"model.visual.blocks.15.attn.proj",
	"model.visual.blocks.15.mlp.fc1",
	"model.visual.blocks.15.mlp.fc2",
	"model.visual.blocks.16.attn.qkv",
	"model.visual.blocks.16.attn.proj",
	"model.visual.blocks.16.mlp.fc1",
	"model.visual.blocks.16.mlp.fc2",
	"model.visual.blocks.17.attn.qkv",
	"model.visual.blocks.17.attn.proj",
	"model.visual.blocks.17.mlp.fc1",
	"model.visual.blocks.17.mlp.fc2",
	"model.visual.blocks.18.attn.qkv",
	"model.visual.blocks.18.attn.proj",
	"model.visual.blocks.18.mlp.fc1",
	"model.visual.blocks.18.mlp.fc2",
	"model.visual.blocks.19.attn.qkv",
	"model.visual.blocks.19.attn.proj",
	"model.visual.blocks.19.mlp.fc1",
	"model.visual.blocks.19.mlp.fc2",
	"model.visual.blocks.20.attn.qkv",
	"model.visual.blocks.20.attn.proj",
	"model.visual.blocks.20.mlp.fc1",
	"model.visual.blocks.20.mlp.fc2",
	"model.visual.blocks.21.attn.qkv",
	"model.visual.blocks.21.attn.proj",
	"model.visual.blocks.21.mlp.fc1",
	"model.visual.blocks.21.mlp.fc2",
	"model.visual.blocks.22.attn.qkv",
	"model.visual.blocks.22.attn.proj",
	"model.visual.blocks.22.mlp.fc1",
	"model.visual.blocks.22.mlp.fc2",
	"model.visual.blocks.23.attn.qkv",
	"model.visual.blocks.23.attn.proj",
	"model.visual.blocks.23.mlp.fc1",
	"model.visual.blocks.23.mlp.fc2",
	"model.visual.blocks.24.attn.qkv",
	"model.visual.blocks.24.attn.proj",
	"model.visual.blocks.24.mlp.fc1",
	"model.visual.blocks.24.mlp.fc2",
	"model.visual.blocks.25.attn.qkv",
	"model.visual.blocks.25.attn.proj",
	"model.visual.blocks.25.mlp.fc1",
	"model.visual.blocks.25.mlp.fc2",
	"model.visual.blocks.26.attn.qkv",
	"model.visual.blocks.26.attn.proj",
	"model.visual.blocks.26.mlp.fc1",
	"model.visual.blocks.26.mlp.fc2",
	"model.visual.blocks.27.attn.qkv",
	"model.visual.blocks.27.attn.proj",
	"model.visual.blocks.28.attn.qkv",
	"model.visual.blocks.28.attn.proj",
	"model.visual.blocks.29.attn.qkv",
	"model.visual.blocks.29.attn.proj",
	"model.visual.blocks.29.mlp.fc1",
	"model.visual.blocks.29.mlp.fc2",
	"model.visual.blocks.31.mlp.fc1",
	"model.visual.blocks.31.mlp.fc2",
	"model.visual.merger.mlp.0",
	"model.visual.merger.mlp.2",
	"model.language_model.layers.1.mlp.gate_proj",
	"model.language_model.layers.1.mlp.up_proj",
	"model.language_model.layers.1.mlp.down_proj",
	"lm_head"
	],
	"llm_int8_threshold": 6.0,
	"load_in_4bit": true,
	"load_in_8bit": false,
	"quant_method": "bitsandbytes"
	},
	"rms_norm_eps": 1e-06,
	"rope_scaling": {
	"mrope_section": [
	16,
	24,
	24
	],
	"rope_type": "default",
	"type": "default"
	},
	"rope_theta": 1000000.0,
	"sliding_window": 32768,
	"text_config": {
	"_name_or_path": "unsloth/Qwen2-VL-2B-Instruct",
	"architectures": [
	"Qwen2VLForConditionalGeneration"
	],
	"attention_dropout": 0.0,
	"dtype": "float16",
	"eos_token_id": 151645,
	"hidden_act": "silu",
	"hidden_size": 1536,
	"image_token_id": null,
	"initializer_range": 0.02,
	"intermediate_size": 8960,
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 32768,
	"max_window_layers": 28,
	"model_type": "qwen2_vl_text",
	"num_attention_heads": 12,
	"num_hidden_layers": 28,
	"num_key_value_heads": 2,
	"pad_token_id": 151654,
	"quantization_config": {
	"_load_in_4bit": true,
	"_load_in_8bit": false,
	"bnb_4bit_compute_dtype": "bfloat16",
	"bnb_4bit_quant_storage": "uint8",
	"bnb_4bit_quant_type": "nf4",
	"bnb_4bit_use_double_quant": true,
	"llm_int8_enable_fp32_cpu_offload": false,
	"llm_int8_has_fp16_weight": false,
	"llm_int8_skip_modules": [
	"lm_head",
	"multi_modal_projector",
	"merger",
	"modality_projection",
	"model.layers.1.mlp",
	"visual.blocks.29.mlp",
	"visual.blocks.21.mlp",
	"visual.blocks.24.attn",
	"visual.blocks.26.mlp",
	"visual.blocks.23.attn",
	"visual.blocks.18.mlp",
	"visual.blocks.19.mlp",
	"visual.blocks.22.attn",
	"visual.blocks.17.mlp",
	"visual.blocks.25.attn",
	"visual.blocks.24.mlp",
	"visual.blocks.26.attn",
	"visual.blocks.29.attn",
	"visual.blocks.21.attn",
	"visual.blocks.22.mlp",
	"visual.blocks.14.mlp",
	"visual.blocks.23.mlp",
	"visual.blocks.14.attn",
	"visual.merger.mlp",
	"visual.blocks.16.mlp",
	"visual.blocks.20.mlp",
	"visual.blocks.25.mlp",
	"visual.blocks.13.mlp",
	"visual.blocks.18.attn",
	"visual.blocks.20.attn",
	"visual.blocks.17.attn",
	"visual.blocks.15.mlp",
	"visual.blocks.27.attn",
	"visual.blocks.28.attn",
	"visual.blocks.12.mlp",
	"visual.blocks.16.attn",
	"visual.blocks.19.attn",
	"visual.blocks.15.attn",
	"visual.blocks.11.attn",
	"visual.blocks.13.attn",
	"visual.blocks.12.attn",
	"visual.blocks.10.mlp",
	"visual.blocks.11.mlp",
	"visual.blocks.10.attn",
	"visual.blocks.9.mlp",
	"visual.blocks.5.attn",
	"visual.blocks.9.attn",
	"visual.blocks.4.attn",
	"visual.blocks.6.mlp",
	"visual.blocks.7.mlp",
	"visual.blocks.1.attn",
	"visual.blocks.6.attn",
	"visual.blocks.7.attn",
	"visual.blocks.5.mlp",
	"visual.blocks.8.attn",
	"visual.blocks.8.mlp",
	"visual.blocks.4.mlp",
	"visual.blocks.3.attn",
	"visual.blocks.3.mlp",
	"visual.blocks.1.mlp",
	"visual.blocks.2.mlp",
	"visual.blocks.2.attn",
	"visual.blocks.0.attn",
	"visual.blocks.0.mlp",
	"visual.blocks.31.mlp"
	],
	"llm_int8_threshold": 6.0,
	"load_in_4bit": true,
	"load_in_8bit": false,
	"quant_method": "bitsandbytes"
	},
	"rms_norm_eps": 1e-06,
	"rope_scaling": {
	"mrope_section": [
	16,
	24,
	24
	],
	"rope_type": "default",
	"type": "default"
	},
	"rope_theta": 1000000.0,
	"sliding_window": null,
	"tie_word_embeddings": true,
	"unsloth_fixed": true,
	"use_cache": true,
	"use_sliding_window": false,
	"video_token_id": null,
	"vision_end_token_id": 151653,
	"vision_start_token_id": 151652,
	"vision_token_id": 151654,
	"vocab_size": 151936
	},
	"transformers_version": "4.56.1",
	"unsloth_fixed": true,
	"unsloth_version": "2025.9.1",
	"use_cache": true,
	"use_sliding_window": false,
	"video_token_id": 151656,
	"vision_config": {
	"depth": 32,
	"dtype": "float16",
	"embed_dim": 1280,
	"hidden_act": "quick_gelu",
	"hidden_size": 1536,
	"in_channels": 3,
	"in_chans": 3,
	"initializer_range": 0.02,
	"mlp_ratio": 4,
	"model_type": "qwen2_vl",
	"num_heads": 16,
	"patch_size": 14,
	"spatial_merge_size": 2,
	"spatial_patch_size": 14,
	"temporal_patch_size": 2
	},
	"vision_end_token_id": 151653,
	"vision_start_token_id": 151652,
	"vision_token_id": 151654,
	"vocab_size": 151936
	}