Update README.md

README.md

@@ -247,26 +247,69 @@ The model follows a connection pattern of Vision Encoder → MLP Adapter → Lan
 ---
 
 
-## 5. Quick Start
+## 5. Usage
 
-This section describes how to quickly install, configure, and run the Skywork-R1V model.
+```python
+from transformers import AutoTokenizer, AutoConfig, AutoModel, CLIPImageProcessor
+from utils_ import split_model, load_image
+import sys, os
+import torch
 
-**Example Steps:**
 
-1. **Clone GitHub repository**
-```bash
-git clone https://github.com/your-repo
-```
+path = 'Skywork/Skywork-R1V-38B'
+image_path = "/path/to/image"
 
-2. **Install dependencies**
-```bash
-cd your-repo
-pip install -r requirements.txt
-```
 
-3. **Run example code**
-```bash
-python demo.py
+device_map, visible_devices = split_model(path)
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    load_in_8bit=False,
+    low_cpu_mem_usage=True,
+    use_flash_attn=True,
+    trust_remote_code=True,
+    device_map=device_map).eval()
+    
+generation_config = dict(max_new_tokens=64000, do_sample=True, temperature=0.6, top_p=0.95, repetition_penalty=1.05)
+pixel_values = load_image(image_path, max_num=12).to(torch.bfloat16).cuda()
+
+# pure-text conversation (纯文本对话)
+question = 'If all cats can fly, and Tom is a cat, can Tom fly?'
+response = model.chat(tokenizer, None, question, generation_config, history=None)
+print(f'User: {question}\nAssistant: {response}')
+
+# single-image single-round conversation (单图单轮对话)
+question = '<image>\nSelect the correct option from this question.'
+response = model.chat(tokenizer, pixel_values, question, generation_config)
+print(f'User: {question}\nAssistant: {response}')
+
+# single-image multi-round conversation (单图多轮对话)
+question = '<image>\nSelect the correct option from this question.'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
+print(f'User: {question}\nAssistant: {response}')
+
+question = 'What if the height in the question is changed to 0.5?'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
+print(f'User: {question}\nAssistant: {response}')
+
+# multi-image multi-round conversation, separate images (多图多轮对话，独立图像)
+pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
+pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
+pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
+num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
+
+question = '<image>\n<image>\nSelect the correct option from this question.'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+                               num_patches_list=num_patches_list,
+                               history=None, return_history=True)
+print(f'User: {question}\nAssistant: {response}')
+
+question = 'What if the height in the question is changed to 0.5?'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+                               num_patches_list=num_patches_list,
+                               history=history, return_history=True)
+print(f'User: {question}\nAssistant: {response}')
 ```
 
 ---