Spaces:
Running
Running
File size: 4,927 Bytes
8704dff |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
#!/usr/bin/env python3
"""
Test script for GGUF model loading in Hugging Face Spaces
This helps identify issues before they cause 500 errors in production
"""
import os
import sys
import time
import logging
# Configure logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)
def test_gguf_loading():
"""Test GGUF model loading with the same parameters used in production"""
# Set environment variables for Hugging Face Spaces
os.environ['HF_HOME'] = '/tmp/huggingface'
os.environ['GGUF_N_THREADS'] = '2'
os.environ['GGUF_N_BATCH'] = '64'
try:
logger.info("Testing GGUF model loading...")
# Test the exact model name from your API call
model_name = "microsoft/Phi-3-mini-4k-instruct-gguf"
filename = "Phi-3-mini-4k-instruct-q4.gguf"
logger.info(f"Model: {model_name}")
logger.info(f"Filename: {filename}")
# Test import
try:
from ai_med_extract.utils.model_loader_gguf import GGUFModelPipeline
logger.info("✓ GGUFModelPipeline import successful")
except ImportError as e:
logger.error(f"✗ Failed to import GGUFModelPipeline: {e}")
return False
# Test model loading with timeout
start_time = time.time()
try:
pipeline = GGUFModelPipeline(model_name, filename, timeout=300)
load_time = time.time() - start_time
logger.info(f"✓ Model loaded successfully in {load_time:.2f}s")
except Exception as e:
load_time = time.time() - start_time
logger.error(f"✗ Model loading failed after {load_time:.2f}s: {e}")
return False
# Test basic generation
try:
test_prompt = "Generate a brief medical summary: Patient has fever and cough."
logger.info("Testing basic generation...")
start_gen = time.time()
result = pipeline.generate(test_prompt, max_tokens=100)
gen_time = time.time() - start_gen
logger.info(f"✓ Generation successful in {gen_time:.2f}s")
logger.info(f"Generated text length: {len(result)} characters")
logger.info(f"Sample output: {result[:200]}...")
except Exception as e:
logger.error(f"✗ Generation failed: {e}")
return False
# Test full summary generation
try:
logger.info("Testing full summary generation...")
start_summary = time.time()
summary = pipeline.generate_full_summary(test_prompt, max_tokens=200, max_loops=1)
summary_time = time.time() - start_summary
logger.info(f"✓ Full summary generation successful in {summary_time:.2f}s")
logger.info(f"Summary length: {len(summary)} characters")
except Exception as e:
logger.error(f"✗ Full summary generation failed: {e}")
return False
logger.info("🎉 All tests passed! GGUF model is working correctly.")
return True
except Exception as e:
logger.error(f"✗ Test failed with unexpected error: {e}")
return False
def test_fallback_pipeline():
"""Test the fallback pipeline when GGUF fails"""
try:
logger.info("Testing fallback pipeline...")
from ai_med_extract.utils.model_loader_gguf import create_fallback_pipeline
fallback = create_fallback_pipeline()
result = fallback.generate("Test prompt")
logger.info(f"✓ Fallback pipeline working: {len(result)} characters generated")
return True
except Exception as e:
logger.error(f"✗ Fallback pipeline failed: {e}")
return False
def main():
"""Main test function"""
logger.info("Starting GGUF model tests...")
# Test 1: GGUF model loading
gguf_success = test_gguf_loading()
# Test 2: Fallback pipeline
fallback_success = test_fallback_pipeline()
# Summary
logger.info("\n" + "="*50)
logger.info("TEST SUMMARY")
logger.info("="*50)
logger.info(f"GGUF Model Loading: {'✓ PASS' if gguf_success else '✗ FAIL'}")
logger.info(f"Fallback Pipeline: {'✓ PASS' if fallback_success else '✗ PASS'}")
if gguf_success:
logger.info("🎉 GGUF model is working correctly!")
logger.info("Your API should work without 500 errors.")
else:
logger.warning("⚠️ GGUF model has issues. The fallback will be used.")
logger.info("Your API will still work but with reduced functionality.")
return gguf_success
if __name__ == "__main__":
success = main()
sys.exit(0 if success else 1)
|