From 398bedb287ba91b1034549d4a31547c9e5ed1616 Mon Sep 17 00:00:00 2001
From: akawrykow <a.kawrykow@gmail.com>
Date: Tue, 22 Aug 2023 17:25:04 -0700
Subject: [PATCH] [gguf] Add git commit hash

---
 convert.py | 7 ++++++-
 gguf.py    | 4 ++++
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/convert.py b/convert.py
index ef5d4cc9d..ac0f3bb9e 100644
--- a/convert.py
+++ b/convert.py
@@ -16,6 +16,7 @@ import pickle
 import re
 import signal
 import struct
+import subprocess
 import sys
 import zipfile
 import numpy as np
@@ -735,7 +736,8 @@ class OutputFile:
 
     def add_meta_arch(self, params: Params) -> None:
         self.gguf.add_name                ("LLaMA")
-        self.gguf.add_date(datetime.today().isoformat())
+        self.gguf.add_date                (datetime.today().isoformat())
+        self.gguf.add_commit_hash         (get_git_revision_short_hash())
         self.gguf.add_context_length      (params.n_ctx)
         self.gguf.add_embedding_length    (params.n_embd)
         self.gguf.add_block_count         (params.n_layer)
@@ -1002,6 +1004,9 @@ def do_dump_model(model_plus: ModelPlus) -> None:
         print(f"{name}: shape={lazy_tensor.shape} type={lazy_tensor.data_type}; {lazy_tensor.description}")
 
 
+def get_git_revision_short_hash() -> str:
+    return subprocess.check_output(['git', 'rev-parse', '--short', 'HEAD']).decode('ascii').strip()
+
 def main(args_in: Optional[List[str]] = None) -> None:
     parser = argparse.ArgumentParser(description="Convert a LLaMa model to a GGML compatible file")
     parser.add_argument("--dump",        action="store_true",    help="don't convert, just show what's in the model")
diff --git a/gguf.py b/gguf.py
index 07a4c2d02..89cbbf93d 100644
--- a/gguf.py
+++ b/gguf.py
@@ -28,6 +28,7 @@ KEY_GENERAL_SOURCE_URL           = "general.source.url"
 KEY_GENERAL_SOURCE_HF_REPO       = "general.source.hugginface.repository"
 KEY_GENERAL_FILE_TYPE            = "general.file_type"
 KEY_GENERAL_DATE                 = "general.date"
+KEY_GENERAL_COMMIT_HASH          = "general.commit_hash"
 
 # LLM
 KEY_LLM_CONTEXT_LENGTH        = "{arch}.context_length"
@@ -603,6 +604,9 @@ class GGUFWriter:
     def add_date(self, date: str):
         self.add_string(KEY_GENERAL_DATE, date)
 
+    def add_commit_hash(self, commit_hash: str):
+        self.add_string(KEY_GENERAL_COMMIT_HASH, commit_hash)
+
     def add_name(self, name: str):
         self.add_string(KEY_GENERAL_NAME, name)