mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-03-17 16:44:07 +00:00
fd1085ffb7
* model-conversion : use CONVERTED_MODEL value for converted model [no ci] This commit updates the model verification scripts to use the CONVERTED_MODEL environment variable instead of using the MODEL_PATH (the original model path) as the basis for the converted model file name. The motivation for this that currently if the converted model file name differs from the original model directory/name the verification scripts will look for the wrong .bin files that were generating when running the models. For example, the following steps were not possible: ```console (venv) $ huggingface-cli download google/gemma-3-270m-it --local-dir ggml-org/gemma-3-270m (venv) $ python3 convert_hf_to_gguf.py ggml-org/gemma-3-270m --outfile test-bf16.gguf --outtype bf16 (venv) $ cd examples/model-conversion/ (venv) $ export MODEL_PATH=../../ggml-org/gemma-3-270m (venv) $ export CONVERTED_MODEL=../../test-bf16.gguf (venv) $ make causal-verify-logits ... Data saved to data/llamacpp-test-bf16.bin Data saved to data/llamacpp-test-bf16.txt Error: llama.cpp logits file not found: data/llamacpp-gemma-3-270m.bin Please run scripts/run-converted-model.sh first to generate this file. make: *** [Makefile:62: causal-verify-logits] Error 1 ``` With the changes in this commit, the above steps will now work as expected.
81 lines
2.7 KiB
Python
Executable File
81 lines
2.7 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
import sys
|
|
import numpy as np
|
|
from pathlib import Path
|
|
|
|
# Add utils directory to path for direct script execution
|
|
sys.path.insert(0, str(Path(__file__).parent.parent / "utils"))
|
|
from common import get_model_name_from_env_path # type: ignore[import-not-found]
|
|
|
|
def quick_logits_check(pytorch_file, llamacpp_file):
|
|
"""Lightweight sanity check before NMSE"""
|
|
|
|
try:
|
|
pytorch_logits = np.fromfile(pytorch_file, dtype=np.float32)
|
|
llamacpp_logits = np.fromfile(llamacpp_file, dtype=np.float32)
|
|
except Exception as e:
|
|
print(f"❌ NOK: Failed to load files - {e}")
|
|
return False
|
|
|
|
# Check shapes match
|
|
if pytorch_logits.shape != llamacpp_logits.shape:
|
|
print(f"❌ NOK: Shape mismatch - PyTorch: {pytorch_logits.shape}, llama.cpp: {llamacpp_logits.shape}")
|
|
return False
|
|
|
|
# Calculate key metrics
|
|
diff = pytorch_logits - llamacpp_logits
|
|
abs_diff = np.abs(diff)
|
|
max_diff = np.max(abs_diff)
|
|
|
|
# Get top 10 predictions from both models
|
|
pytorch_top10 = np.argsort(pytorch_logits)[-10:][::-1]
|
|
llamacpp_top10 = np.argsort(llamacpp_logits)[-10:][::-1]
|
|
print(f"Top 10 PyTorch logits: {pytorch_logits[pytorch_top10]}")
|
|
print(f"Top 10 llama.cpp logits: {llamacpp_logits[llamacpp_top10]}")
|
|
print(f"Max absolute difference: {max_diff:.4f}")
|
|
|
|
return True
|
|
|
|
def main():
|
|
model_name = get_model_name_from_env_path('MODEL_PATH')
|
|
data_dir = Path("data")
|
|
pytorch_file = data_dir / f"pytorch-{model_name}.bin"
|
|
|
|
llamacpp_model_name = get_model_name_from_env_path('CONVERTED_MODEL')
|
|
print(f"Using converted model: {llamacpp_model_name}")
|
|
llamacpp_file = data_dir / f"llamacpp-{llamacpp_model_name}.bin"
|
|
|
|
if not pytorch_file.exists():
|
|
print(f"Error: PyTorch logits file not found: {pytorch_file}")
|
|
print("Please run scripts/run-org-model.sh first to generate this file.")
|
|
sys.exit(1)
|
|
|
|
if not llamacpp_file.exists():
|
|
print(f"Error: llama.cpp logits file not found: {llamacpp_file}")
|
|
print("Please run scripts/run-converted-model.sh first to generate this file.")
|
|
sys.exit(1)
|
|
|
|
print("Checked all required files were found. Proceeding...\n")
|
|
|
|
|
|
print("🔍 GGML Model Validation for model ", model_name)
|
|
print("=" * 40)
|
|
print(f"PyTorch logits : {pytorch_file}")
|
|
print(f"llama.cpp logits: {llamacpp_file}")
|
|
print()
|
|
|
|
success = quick_logits_check(pytorch_file, llamacpp_file)
|
|
|
|
# Exit with appropriate code
|
|
if success:
|
|
print("✅ OK: Lightweight model check successful!")
|
|
print(" Ok to proceed with NMSE check...")
|
|
sys.exit(0)
|
|
else:
|
|
print(f"❌ NOK: Top 10 predictions don't match - generation will differ")
|
|
sys.exit(1)
|
|
|
|
if __name__ == "__main__":
|
|
main()
|