Instructions to use hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug with Transformers:

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

pipe = pipeline("image-text-to-text", model="hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug")
model = AutoModelForMultimodalLM.from_pretrained("hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug

SGLang

How to use hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug 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 "hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug with Docker Model Runner:
```
docker model run hf.co/hoanglv7501/Qwen2.5-VL-3B-Instruct-bnb-4bit-FixEOSbug
```

hoanglv7501 commited on Jun 18, 2025

Commit

b192228

verified ·

1 Parent(s): 53d9fd7

Update config.json

Browse files

Files changed (1) hide show

config.json +86 -86

config.json CHANGED Viewed

@@ -1,86 +1,86 @@
-{
-  "architectures": [
-    "Qwen2_5_VLForConditionalGeneration"
-  ],
-  "attention_dropout": 0.0,
-  "eos_token_id": 151645,
-  "hidden_act": "silu",
-  "hidden_size": 2048,
-  "image_token_id": 151655,
-  "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 128000,
-  "max_window_layers": 70,
-  "model_type": "qwen2_5_vl",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 36,
-  "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"
-    ],
-    "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,
-  "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
-  "unsloth_fixed": true,
-  "use_cache": true,
-  "use_sliding_window": false,
-  "video_token_id": 151656,
-  "vision_config": {
-    "depth": 32,
-    "fullatt_block_indexes": [
-      7,
-      15,
-      23,
-      31
-    ],
-    "hidden_act": "silu",
-    "hidden_size": 1280,
-    "in_channels": 3,
-    "in_chans": 3,
-    "intermediate_size": 3420,
-    "model_type": "qwen2_5_vl",
-    "num_heads": 16,
-    "out_hidden_size": 2048,
-    "patch_size": 14,
-    "spatial_merge_size": 2,
-    "spatial_patch_size": 14,
-    "temporal_patch_size": 2,
-    "tokens_per_second": 2,
-    "torch_dtype": "bfloat16",
-    "window_size": 112
-  },
-  "vision_end_token_id": 151653,
-  "vision_start_token_id": 151652,
-  "vision_token_id": 151654,
-  "vocab_size": 151936
-}

+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "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"
+    ],
+    "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,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 2048,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}