mlx-gpt-oss-120b/analyze_model.py

#!/usr/bin/env python3
"""
Comprehensive analysis of the GPT-OSS-120B model
"""

from transformers import AutoTokenizer, AutoConfig
import json
import logging
from pathlib import Path

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

def analyze_model():
    """Comprehensive model analysis"""
    model_path = "./my_model"
    
    logger.info("=" * 60)
    logger.info("🔍 GPT-OSS-120B-MXFP4-Q4 Comprehensive Analysis")
    logger.info("=" * 60)
    
    # Load config
    config = AutoConfig.from_pretrained(model_path)
    logger.info("📊 Model Configuration:")
    logger.info(f"   Architecture: {config.architectures[0]}")
    logger.info(f"   Model type: {config.model_type}")
    logger.info(f"   Vocab size: {config.vocab_size:,}")
    logger.info(f"   Hidden size: {config.hidden_size}")
    logger.info(f"   Num hidden layers: {config.num_hidden_layers}")
    logger.info(f"   Num attention heads: {config.num_attention_heads}")
    logger.info(f"   Max position embeddings: {config.max_position_embeddings}")
    
    # Load tokenizer
    tokenizer = AutoTokenizer.from_pretrained(model_path)
    logger.info("\n🔤 Tokenizer Analysis:")
    logger.info(f"   Vocabulary size: {tokenizer.vocab_size:,}")
    logger.info(f"   Special tokens: {len(tokenizer.special_tokens_map)}")
    logger.info(f"   Padding token: {tokenizer.pad_token}")
    logger.info(f"   EOS token: {tokenizer.eos_token}")
    
    # Test various prompts
    test_prompts = [
        "The capital of France is",
        "Artificial intelligence is",
        "The future of machine learning will",
        "Once upon a time",
        "import numpy as np",
        "量子コンピューティングとは",  # Japanese
        "El aprendizaje automático es",  # Spanish
        "机器学习是",  # Chinese
        "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\nHello!<|im_end|>\n<|im_start|>assistant"
    ]
    
    logger.info("\n🧪 Tokenization Examples:")
    for prompt in test_prompts:
        tokens = tokenizer.encode(prompt)
        decoded = tokenizer.decode(tokens[:10]) + ("..." if len(tokens) > 10 else "")
        logger.info(f"   '{prompt[:30]}{'...' if len(prompt) > 30 else ''}'")
        logger.info(f"     → {len(tokens)} tokens: {tokens[:10]}{'...' if len(tokens) > 10 else ''}")
        logger.info(f"     → decoded: {decoded}")
    
    # Check model files
    model_files = list(Path(model_path).glob("*.safetensors"))
    logger.info(f"\n📦 Model Files: {len(model_files)} safetensors files")
    
    # Estimate memory requirements
    total_params = 120_000_000_000  # 120B parameters
    param_size = 0.5  # bytes per parameter for 4-bit quantization
    total_memory_gb = (total_params * param_size) / (1024 ** 3)
    
    logger.info("\n💾 Memory Requirements (Estimated):")
    logger.info(f"   Model size (4-bit): ~{total_memory_gb:.1f} GB")
    logger.info(f"   Inference RAM: ~{total_memory_gb * 1.5:.1f} GB+")
    logger.info(f"   GPU VRAM: ~{total_memory_gb:.1f} GB+ (recommended)")
    
    return config, tokenizer

if __name__ == "__main__":
    analyze_model()