File size: 3,069 Bytes
27320e1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 |
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
TIGeR Model Usage Examples
Demonstrates how to use the fine-tuned spatial reasoning model
"""
import os
import sys
import json
import re
from typing import List, Dict, Any, Optional
from llamafactory.chat.chat_model import ChatModel
def load_model(config_file: str):
"""Load model using LLaMA-Factory ChatModel"""
print(f"Loading model with config: {config_file}")
try:
# Simulate command line arguments
original_argv = sys.argv.copy()
sys.argv = [sys.argv[0], config_file]
try:
chat_model = ChatModel()
print("✅ Model loaded successfully!")
return chat_model
finally:
# Restore original command line arguments
sys.argv = original_argv
except Exception as e:
print(f"❌ Model loading failed: {e}")
return None
def single_inference_demo(chat_model):
"""Single image inference demonstration"""
print("\n" + "="*50)
print("Single Image Inference Demo")
print("="*50)
# Image path - replace with your actual image path
image_paths = [
"/path/to/your/image.jpg" # Replace with actual image path
]
# Question - using the same format as TIGeR
question = "Two points are circled on the image, labeled by A and B beside each circle. Which point is closer to the camera? Select from the following choices.\n(A) A is closer\n(B) B is closer"
try:
print(f"📷 Loading image: {image_paths[0]}")
print(f"🔍 Question: {question}")
# Prepare messages in the format expected by ChatModel
messages = [
{
"role": "user",
"content": question
}
]
# Get model response
response = chat_model.chat(messages, images=image_paths)
assistant_texts = []
for resp in response:
try:
assistant_texts.append(resp.response_text)
except Exception:
assistant_texts.append(str(resp))
response_text = "\n".join(assistant_texts)
print(f"💡 Answer: {response_text}")
except FileNotFoundError:
print("❌ Image file not found, please provide correct image path")
except Exception as e:
print(f"❌ Error occurred during processing: {e}")
def main():
"""Main function"""
print("🚀 TIGeR Model Usage Examples")
print("="*60)
# Configuration file path - using the config file in the same directory
config_file = "glm4v_tisr_full_inference.yaml"
# Load model
chat_model = load_model(config_file)
if chat_model is None:
print("❌ Failed to load model. Please check the config file path.")
return
# Run single inference demo
single_inference_demo(chat_model)
print("\n" + "="*60)
print("✅ Demo completed!")
print("="*60)
if __name__ == "__main__":
main()
|