From eac2e83f9f26f15f28e09236a30584b1503d95f5 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Sun, 12 May 2024 19:51:55 -0400
Subject: [PATCH 01/19] gguf: Add example script for extracting chat template

---
 gguf-py/scripts/gguf-template.py | 103 +++++++++++++++++++++++++++++++
 1 file changed, 103 insertions(+)
 create mode 100644 gguf-py/scripts/gguf-template.py

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
new file mode 100644
index 0000000000000..301b416283452
--- /dev/null
+++ b/gguf-py/scripts/gguf-template.py
@@ -0,0 +1,103 @@
+"""
+gguf_chat_template.py - example file to extract the chat template from the models metadata
+"""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import os
+import sys
+from pathlib import Path
+
+import jinja2
+
+# Necessary to load the local gguf package
+if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent / 'gguf-py').exists():
+    sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from gguf.constants import Keys
+from gguf.gguf_reader import GGUFReader  # noqa: E402
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger("gguf-chat-template")
+
+
+def get_chat_template(model_file: str) -> str:
+    reader = GGUFReader(model_file)
+
+    # Available keys
+    logger.info("Detected model metadata!")
+    logger.info("Outputting available model fields:")
+    for key in reader.fields.keys():
+        logger.info(key)
+
+    # Access the 'chat_template' field directly using its key
+    chat_template_field = reader.fields.get(Keys.Tokenizer.CHAT_TEMPLATE)
+
+    if chat_template_field:
+        # Extract the chat template string from the field
+        chat_template_memmap = chat_template_field.parts[-1]
+        chat_template_string = chat_template_memmap.tobytes().decode("utf-8")
+        return chat_template_string
+    else:
+        logger.error("Chat template field not found in model metadata.")
+        return ""
+
+
+def display_chat_template(chat_template: str, format_template: bool = False):
+    """
+    Display the chat template to standard output, optionally formatting it using Jinja2.
+
+    Args:
+        chat_template (str): The extracted chat template.
+        format_template (bool, optional): Whether to format the template using Jinja2. Defaults to False.
+    """
+    logger.info(f"Format Template: {format_template}")
+
+    if format_template:
+        # Render the formatted template using Jinja2 with a context that includes 'bos_token' and 'eos_token'
+        env = jinja2.Environment(
+            loader=jinja2.BaseLoader(),
+            trim_blocks=True,
+            lstrip_blocks=True,
+        )
+        logger.info(chat_template)
+        template = env.from_string(chat_template)
+        formatted_template = template.render(
+            messages=[
+                {"role": "system", "content": "I am a helpful assistant."},
+                {"role": "user", "content": "Hello!"},
+            ],
+            bos_token="[BOS]",
+            eos_token="[EOS]",
+        )
+        print(formatted_template)
+    else:
+        # Display the raw template
+        print(chat_template)
+
+
+# Example usage:
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Extract chat template from a GGUF model file"
+    )
+    parser.add_argument("model_file", type=str, help="Path to the GGUF model file")
+    parser.add_argument(
+        "--format",
+        action="store_true",
+        help="Format the chat template using Jinja2",
+    )
+
+    args = parser.parse_args()
+
+    model_file = args.model_file
+    chat_template = get_chat_template(model_file)
+
+    display_chat_template(chat_template, format_template=args.format)
+
+
+if __name__ == "__main__":
+    main()

From bf5154f9bc717118b20738982902a3e8f738896c Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Sun, 12 May 2024 20:07:30 -0400
Subject: [PATCH 02/19] docs: Fix filename in docstring and remove return type
 from main

---
 gguf-py/scripts/gguf-template.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index 301b416283452..cfa8bbfb3633c 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -1,5 +1,5 @@
 """
-gguf_chat_template.py - example file to extract the chat template from the models metadata
+gguf-template.py - example file to extract the chat template from the models metadata
 """
 
 from __future__ import annotations
@@ -80,7 +80,7 @@ def display_chat_template(chat_template: str, format_template: bool = False):
 
 
 # Example usage:
-def main() -> None:
+def main():
     parser = argparse.ArgumentParser(
         description="Extract chat template from a GGUF model file"
     )

From 4a018e706f0be37c0d4aa6a44a7dd43d3811eca0 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Sun, 12 May 2024 20:08:37 -0400
Subject: [PATCH 03/19] feat: Add assistant turn

---
 gguf-py/scripts/gguf-template.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index cfa8bbfb3633c..dff9023ca320c 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -69,6 +69,7 @@ def display_chat_template(chat_template: str, format_template: bool = False):
             messages=[
                 {"role": "system", "content": "I am a helpful assistant."},
                 {"role": "user", "content": "Hello!"},
+                {"role": "assistant", "content": "Hello! How may I assist you today?"},
             ],
             bos_token="[BOS]",
             eos_token="[EOS]",

From 8b9ed888bca7e5cd44880306b1041e2d92fab028 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Sun, 12 May 2024 20:17:35 -0400
Subject: [PATCH 04/19] patch: Handle how templates are rendered if no system
 prompt is allowed

---
 gguf-py/scripts/gguf-template.py | 37 +++++++++++++++++++++-----------
 1 file changed, 24 insertions(+), 13 deletions(-)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index dff9023ca320c..1f5408965f56d 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -59,21 +59,32 @@ def display_chat_template(chat_template: str, format_template: bool = False):
     if format_template:
         # Render the formatted template using Jinja2 with a context that includes 'bos_token' and 'eos_token'
         env = jinja2.Environment(
-            loader=jinja2.BaseLoader(),
-            trim_blocks=True,
-            lstrip_blocks=True,
+            loader=jinja2.BaseLoader(), trim_blocks=True, lstrip_blocks=True
         )
-        logger.info(chat_template)
         template = env.from_string(chat_template)
-        formatted_template = template.render(
-            messages=[
-                {"role": "system", "content": "I am a helpful assistant."},
-                {"role": "user", "content": "Hello!"},
-                {"role": "assistant", "content": "Hello! How may I assist you today?"},
-            ],
-            bos_token="[BOS]",
-            eos_token="[EOS]",
-        )
+
+        messages = [
+            {"role": "system", "content": "I am a helpful assistant."},
+            {"role": "user", "content": "Hello!"},
+            {"role": "assistant", "content": "Hello! How may I assist you today?"},
+        ]
+        bos_token = "<s>"
+        eos_token = "</s>"
+
+        try:
+            formatted_template = template.render(
+                messages=messages,
+                bos_token=bos_token,
+                eos_token=eos_token,
+            )
+        except jinja2.exceptions.UndefinedError:
+            # system message is incompatible with set format
+            formatted_template = template.render(
+                messages=messages[1:],
+                bos_token=bos_token,
+                eos_token=eos_token,
+            )
+
         print(formatted_template)
     else:
         # Display the raw template

From 668c7ee6c51506b2798bed8b5beb074670c407be Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Sun, 12 May 2024 20:37:27 -0400
Subject: [PATCH 05/19] refactor: Use render template instead of format

---
 gguf-py/scripts/gguf-template.py | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index 1f5408965f56d..b29c27c745c40 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -46,17 +46,17 @@ def get_chat_template(model_file: str) -> str:
         return ""
 
 
-def display_chat_template(chat_template: str, format_template: bool = False):
+def display_chat_template(chat_template: str, render_template: bool = False):
     """
     Display the chat template to standard output, optionally formatting it using Jinja2.
 
     Args:
         chat_template (str): The extracted chat template.
-        format_template (bool, optional): Whether to format the template using Jinja2. Defaults to False.
+        render_template (bool, optional): Whether to format the template using Jinja2. Defaults to False.
     """
-    logger.info(f"Format Template: {format_template}")
+    logger.info(f"Format Template: {render_template}")
 
-    if format_template:
+    if render_template:
         # Render the formatted template using Jinja2 with a context that includes 'bos_token' and 'eos_token'
         env = jinja2.Environment(
             loader=jinja2.BaseLoader(), trim_blocks=True, lstrip_blocks=True
@@ -98,9 +98,10 @@ def main():
     )
     parser.add_argument("model_file", type=str, help="Path to the GGUF model file")
     parser.add_argument(
-        "--format",
+        "-r",
+        "--render-template",
         action="store_true",
-        help="Format the chat template using Jinja2",
+        help="Render the chat template using Jinja2",
     )
 
     args = parser.parse_args()
@@ -108,7 +109,7 @@ def main():
     model_file = args.model_file
     chat_template = get_chat_template(model_file)
 
-    display_chat_template(chat_template, format_template=args.format)
+    display_chat_template(chat_template, render_template=args.render_template)
 
 
 if __name__ == "__main__":

From fa0b0b10ccd0bc678d01b1c0aa0a33681ece9595 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Sun, 12 May 2024 20:39:55 -0400
Subject: [PATCH 06/19] feat: Allow toggling verbosity

---
 gguf-py/scripts/gguf-template.py | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index b29c27c745c40..d3757b4f39004 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -24,14 +24,15 @@
 logger = logging.getLogger("gguf-chat-template")
 
 
-def get_chat_template(model_file: str) -> str:
+def get_chat_template(model_file: str, verbose: bool = False) -> str:
     reader = GGUFReader(model_file)
 
     # Available keys
     logger.info("Detected model metadata!")
-    logger.info("Outputting available model fields:")
-    for key in reader.fields.keys():
-        logger.info(key)
+    if verbose:
+        logger.info("Outputting available model fields:")
+        for key in reader.fields.keys():
+            logger.info(key)
 
     # Access the 'chat_template' field directly using its key
     chat_template_field = reader.fields.get(Keys.Tokenizer.CHAT_TEMPLATE)
@@ -103,12 +104,16 @@ def main():
         action="store_true",
         help="Render the chat template using Jinja2",
     )
-
+    parser.add_argument(
+        "-v",
+        "--verbose",
+        action="store_true",
+        help="Output model keys",
+    )
     args = parser.parse_args()
 
     model_file = args.model_file
-    chat_template = get_chat_template(model_file)
-
+    chat_template = get_chat_template(model_file, args.verbose)
     display_chat_template(chat_template, render_template=args.render_template)
 
 

From 6be3576e014e82b2f33f2e900e5bf03d808a36d7 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Sun, 12 May 2024 20:48:29 -0400
Subject: [PATCH 07/19] feat: Add sane defaults and options for setting special
 tokens

---
 gguf-py/scripts/gguf-template.py | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index d3757b4f39004..e5f80c69d42a8 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -47,7 +47,9 @@ def get_chat_template(model_file: str, verbose: bool = False) -> str:
         return ""
 
 
-def display_chat_template(chat_template: str, render_template: bool = False):
+def display_chat_template(
+    chat_template: str, bos_token: str, eos_token: str, render_template: bool = False
+):
     """
     Display the chat template to standard output, optionally formatting it using Jinja2.
 
@@ -68,9 +70,9 @@ def display_chat_template(chat_template: str, render_template: bool = False):
             {"role": "system", "content": "I am a helpful assistant."},
             {"role": "user", "content": "Hello!"},
             {"role": "assistant", "content": "Hello! How may I assist you today?"},
+            {"role": "user", "content": "Can you tell me what pickled mayonnaise is?"},
+            {"role": "assistant", "content": "Certainly! What would you like to know about it?"},
         ]
-        bos_token = "<s>"
-        eos_token = "</s>"
 
         try:
             formatted_template = template.render(
@@ -104,6 +106,18 @@ def main():
         action="store_true",
         help="Render the chat template using Jinja2",
     )
+    parser.add_argument(
+        "-b",
+        "--bos",
+        default="<s>",
+        help="Set a bos special token. Default is '<s>'.",
+    )
+    parser.add_argument(
+        "-e",
+        "--eos",
+        default="</s>",
+        help="Set a eos special token. Default is '</s>'.",
+    )
     parser.add_argument(
         "-v",
         "--verbose",
@@ -114,7 +128,9 @@ def main():
 
     model_file = args.model_file
     chat_template = get_chat_template(model_file, args.verbose)
-    display_chat_template(chat_template, render_template=args.render_template)
+    display_chat_template(
+        chat_template, args.bos, args.eos, render_template=args.render_template
+    )
 
 
 if __name__ == "__main__":

From 214e9e6f0b67d288e0d40125c3c551252d7614e4 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Sun, 12 May 2024 21:07:05 -0400
Subject: [PATCH 08/19] refactor: Add logging debug and clean up logger
 implementation

---
 gguf-py/scripts/gguf-template.py | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index e5f80c69d42a8..aa042db77d542 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -20,19 +20,17 @@
 from gguf.gguf_reader import GGUFReader  # noqa: E402
 
 # Configure logging
-logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger("gguf-chat-template")
 
 
-def get_chat_template(model_file: str, verbose: bool = False) -> str:
+def get_chat_template(model_file: str) -> str:
     reader = GGUFReader(model_file)
 
     # Available keys
-    logger.info("Detected model metadata!")
-    if verbose:
-        logger.info("Outputting available model fields:")
-        for key in reader.fields.keys():
-            logger.info(key)
+    logger.debug("Detected model metadata!")
+    logger.debug("Outputting available model fields:")
+    for key in reader.fields.keys():
+        logger.debug(key)
 
     # Access the 'chat_template' field directly using its key
     chat_template_field = reader.fields.get(Keys.Tokenizer.CHAT_TEMPLATE)
@@ -57,7 +55,7 @@ def display_chat_template(
         chat_template (str): The extracted chat template.
         render_template (bool, optional): Whether to format the template using Jinja2. Defaults to False.
     """
-    logger.info(f"Format Template: {render_template}")
+    logger.debug(f"Render Template: {render_template}")
 
     if render_template:
         # Render the formatted template using Jinja2 with a context that includes 'bos_token' and 'eos_token'
@@ -126,8 +124,12 @@ def main():
     )
     args = parser.parse_args()
 
-    model_file = args.model_file
-    chat_template = get_chat_template(model_file, args.verbose)
+    if args.verbose:
+        logging.basicConfig(level=logging.DEBUG)
+    else:
+        logging.basicConfig(level=logging.INFO)
+
+    chat_template = get_chat_template(args.model_file)
     display_chat_template(
         chat_template, args.bos, args.eos, render_template=args.render_template
     )

From f8bb2239249937bb58eeb99d130959dff719e6b7 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Sun, 12 May 2024 21:17:04 -0400
Subject: [PATCH 09/19] refactor: Remove rename from display to render and
 return result instead of printing

---
 gguf-py/scripts/gguf-template.py | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index aa042db77d542..764a76b8fe444 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -45,9 +45,9 @@ def get_chat_template(model_file: str) -> str:
         return ""
 
 
-def display_chat_template(
+def render_chat_template(
     chat_template: str, bos_token: str, eos_token: str, render_template: bool = False
-):
+) -> str:
     """
     Display the chat template to standard output, optionally formatting it using Jinja2.
 
@@ -86,10 +86,10 @@ def display_chat_template(
                 eos_token=eos_token,
             )
 
-        print(formatted_template)
+        return formatted_template
     else:
         # Display the raw template
-        print(chat_template)
+        return chat_template
 
 
 # Example usage:
@@ -130,9 +130,10 @@ def main():
         logging.basicConfig(level=logging.INFO)
 
     chat_template = get_chat_template(args.model_file)
-    display_chat_template(
+    rendered_template = render_chat_template(
         chat_template, args.bos, args.eos, render_template=args.render_template
     )
+    print(rendered_template)
 
 
 if __name__ == "__main__":

From da96fdd15f8aa3c0f08b23ae1109d0c775272f97 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Mon, 13 May 2024 13:10:44 -0400
Subject: [PATCH 10/19] patch: Apply patch for advisories/GHSA-56xg-wfcc-g829

Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
---
 gguf-py/scripts/gguf-template.py | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index 764a76b8fe444..78d9524752a53 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -11,6 +11,7 @@
 from pathlib import Path
 
 import jinja2
+import jinja2.sandbox
 
 # Necessary to load the local gguf package
 if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent / 'gguf-py').exists():
@@ -46,7 +47,10 @@ def get_chat_template(model_file: str) -> str:
 
 
 def render_chat_template(
-    chat_template: str, bos_token: str, eos_token: str, render_template: bool = False
+    chat_template: str,
+    bos_token: str,
+    eos_token: str,
+    render_template: bool = False,
 ) -> str:
     """
     Display the chat template to standard output, optionally formatting it using Jinja2.
@@ -59,8 +63,8 @@ def render_chat_template(
 
     if render_template:
         # Render the formatted template using Jinja2 with a context that includes 'bos_token' and 'eos_token'
-        env = jinja2.Environment(
-            loader=jinja2.BaseLoader(), trim_blocks=True, lstrip_blocks=True
+        env = jinja2.sandbox.ImmutableSandboxedEnvironment(
+            trim_blocks=True, lstrip_blocks=True
         )
         template = env.from_string(chat_template)
 
@@ -131,9 +135,12 @@ def main():
 
     chat_template = get_chat_template(args.model_file)
     rendered_template = render_chat_template(
-        chat_template, args.bos, args.eos, render_template=args.render_template
+        chat_template,
+        args.bos,
+        args.eos,
+        render_template=args.render_template,
     )
-    print(rendered_template)
+    print(rendered_template)  # noqa: NP100
 
 
 if __name__ == "__main__":

From cfe659d90a589d504c82786e029298312aef0781 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Mon, 13 May 2024 13:12:38 -0400
Subject: [PATCH 11/19] feat: Add option for adding generation prompt

Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
---
 gguf-py/scripts/gguf-template.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index 78d9524752a53..ef2b781484e21 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -50,6 +50,7 @@ def render_chat_template(
     chat_template: str,
     bos_token: str,
     eos_token: str,
+    add_generation_prompt: bool = False,
     render_template: bool = False,
 ) -> str:
     """
@@ -60,6 +61,7 @@ def render_chat_template(
         render_template (bool, optional): Whether to format the template using Jinja2. Defaults to False.
     """
     logger.debug(f"Render Template: {render_template}")
+    logger.debug(f"Add Generation Prompt: {add_generation_prompt}")
 
     if render_template:
         # Render the formatted template using Jinja2 with a context that includes 'bos_token' and 'eos_token'
@@ -81,6 +83,7 @@ def render_chat_template(
                 messages=messages,
                 bos_token=bos_token,
                 eos_token=eos_token,
+                add_generation_prompt=add_generation_prompt,
             )
         except jinja2.exceptions.UndefinedError:
             # system message is incompatible with set format
@@ -88,6 +91,7 @@ def render_chat_template(
                 messages=messages[1:],
                 bos_token=bos_token,
                 eos_token=eos_token,
+                add_generation_prompt=add_generation_prompt,
             )
 
         return formatted_template
@@ -120,6 +124,12 @@ def main():
         default="</s>",
         help="Set a eos special token. Default is '</s>'.",
     )
+    parser.add_argument(
+        "-g",
+        "--agp",
+        action="store_true",
+        help="Add generation prompt. Default is True.",
+    )
     parser.add_argument(
         "-v",
         "--verbose",
@@ -138,6 +148,7 @@ def main():
         chat_template,
         args.bos,
         args.eos,
+        add_generation_prompt=args.agp,
         render_template=args.render_template,
     )
     print(rendered_template)  # noqa: NP100

From b4b6f1fa00373146426de6ad634b7c7723fbeb8e Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Wed, 15 May 2024 12:54:55 -0400
Subject: [PATCH 12/19] fix: End messages with a user role due to jinja2
 conditional checks

Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
---
 gguf-py/scripts/gguf-template.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index ef2b781484e21..27b6e9f3c7861 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -76,6 +76,7 @@ def render_chat_template(
             {"role": "assistant", "content": "Hello! How may I assist you today?"},
             {"role": "user", "content": "Can you tell me what pickled mayonnaise is?"},
             {"role": "assistant", "content": "Certainly! What would you like to know about it?"},
+            {"role": "user", "content": "Is it just regular mayonnaise with vinegar or something else?"},
         ]
 
         try:

From 2185e5cf14cdc7e588587d4aa190a152868d4823 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Wed, 15 May 2024 12:58:24 -0400
Subject: [PATCH 13/19] docs: Update and fix CLI help descriptions

Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
---
 gguf-py/scripts/gguf-template.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf-template.py
index 27b6e9f3c7861..43f3bca9e5567 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf-template.py
@@ -111,7 +111,7 @@ def main():
         "-r",
         "--render-template",
         action="store_true",
-        help="Render the chat template using Jinja2",
+        help="Render the chat template using Jinja2. Default is False.",
     )
     parser.add_argument(
         "-b",
@@ -129,13 +129,13 @@ def main():
         "-g",
         "--agp",
         action="store_true",
-        help="Add generation prompt. Default is True.",
+        help="Add generation prompt. Default is False.",
     )
     parser.add_argument(
         "-v",
         "--verbose",
         action="store_true",
-        help="Output model keys",
+        help="Output model keys. Default is False.",
     )
     args = parser.parse_args()
 

From 4204cab3908c7cf712c6a359e00d17761f0586e2 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Sun, 14 Jul 2024 00:34:07 -0400
Subject: [PATCH 14/19] chore : Apply snake case as described in #8305

Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
---
 gguf-py/scripts/{gguf-template.py => gguf_template.py} | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
 rename gguf-py/scripts/{gguf-template.py => gguf_template.py} (98%)

diff --git a/gguf-py/scripts/gguf-template.py b/gguf-py/scripts/gguf_template.py
similarity index 98%
rename from gguf-py/scripts/gguf-template.py
rename to gguf-py/scripts/gguf_template.py
index 43f3bca9e5567..c66224870d83f 100644
--- a/gguf-py/scripts/gguf-template.py
+++ b/gguf-py/scripts/gguf_template.py
@@ -1,5 +1,5 @@
 """
-gguf-template.py - example file to extract the chat template from the models metadata
+gguf_template.py - example file to extract the chat template from the models metadata
 """
 
 from __future__ import annotations

From b7528fdf89d4636f5c44b89e7fd1907d31e42abe Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Mon, 15 Jul 2024 13:56:54 -0400
Subject: [PATCH 15/19] chore : Add jinja2 as dev dependency in pyproject.toml
 and explicit dependency in requirements.txt

---
 gguf-py/pyproject.toml                             | 1 +
 requirements/requirements-convert_legacy_llama.txt | 1 +
 2 files changed, 2 insertions(+)

diff --git a/gguf-py/pyproject.toml b/gguf-py/pyproject.toml
index 62129126bdddc..e1f175e699973 100644
--- a/gguf-py/pyproject.toml
+++ b/gguf-py/pyproject.toml
@@ -25,6 +25,7 @@ tqdm = ">=4.27"
 
 [tool.poetry.dev-dependencies]
 pytest = "^5.2"
+jinja2 = ">=3.1.0"
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]
diff --git a/requirements/requirements-convert_legacy_llama.txt b/requirements/requirements-convert_legacy_llama.txt
index 1d07b09522f61..4950705aa24b4 100644
--- a/requirements/requirements-convert_legacy_llama.txt
+++ b/requirements/requirements-convert_legacy_llama.txt
@@ -1,5 +1,6 @@
 numpy~=1.26.4
 sentencepiece~=0.2.0
 transformers>=4.40.1,<5.0.0
+jinja2>=3.1.0
 gguf>=0.1.0
 protobuf>=4.21.0,<5.0.0

From 0cb404cc13d501ad11beed20b20f68e34b6a43e3 Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Mon, 15 Jul 2024 13:57:46 -0400
Subject: [PATCH 16/19] feat : Add shebang and executable bit to enable script
 execution

---
 gguf-py/scripts/gguf_template.py | 1 +
 1 file changed, 1 insertion(+)
 mode change 100644 => 100755 gguf-py/scripts/gguf_template.py

diff --git a/gguf-py/scripts/gguf_template.py b/gguf-py/scripts/gguf_template.py
old mode 100644
new mode 100755
index c66224870d83f..6bb1c10213c84
--- a/gguf-py/scripts/gguf_template.py
+++ b/gguf-py/scripts/gguf_template.py
@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 """
 gguf_template.py - example file to extract the chat template from the models metadata
 """

From 0de43fcc00f37e300a3dc168f0b8bfde06ea9aac Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Fri, 19 Jul 2024 14:05:21 -0400
Subject: [PATCH 17/19] chore : Set sentencepiece to 0.2.0 to match
 requirements.txt

Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
---
 poetry.lock    | 105 ++++++++++++++++++++++++++-----------------------
 pyproject.toml |   2 +-
 2 files changed, 57 insertions(+), 50 deletions(-)

diff --git a/poetry.lock b/poetry.lock
index eb6baa6c749c0..562e72a00bcd2 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
 
 [[package]]
 name = "atomicwrites"
@@ -543,7 +543,6 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
-    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"},
     {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
     {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
     {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
@@ -835,56 +834,64 @@ torch = ["safetensors[numpy]", "torch (>=1.10)"]
 
 [[package]]
 name = "sentencepiece"
-version = "0.1.99"
+version = "0.2.0"
 description = "SentencePiece python wrapper"
 optional = false
 python-versions = "*"
 files = [
-    {file = "sentencepiece-0.1.99-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0eb528e70571b7c02723e5804322469b82fe7ea418c96051d0286c0fa028db73"},
-    {file = "sentencepiece-0.1.99-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:77d7fafb2c4e4659cbdf303929503f37a26eabc4ff31d3a79bf1c5a1b338caa7"},
-    {file = "sentencepiece-0.1.99-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:be9cf5b9e404c245aeb3d3723c737ba7a8f5d4ba262ef233a431fa6c45f732a0"},
-    {file = "sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:baed1a26464998f9710d20e52607c29ffd4293e7c71c6a1f83f51ad0911ec12c"},
-    {file = "sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9832f08bb372d4c8b567612f8eab9e36e268dff645f1c28f9f8e851be705f6d1"},
-    {file = "sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:019e7535108e309dae2b253a75834fc3128240aa87c00eb80732078cdc182588"},
-    {file = "sentencepiece-0.1.99-cp310-cp310-win32.whl", hash = "sha256:fa16a830416bb823fa2a52cbdd474d1f7f3bba527fd2304fb4b140dad31bb9bc"},
-    {file = "sentencepiece-0.1.99-cp310-cp310-win_amd64.whl", hash = "sha256:14b0eccb7b641d4591c3e12ae44cab537d68352e4d3b6424944f0c447d2348d5"},
-    {file = "sentencepiece-0.1.99-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:6d3c56f24183a1e8bd61043ff2c58dfecdc68a5dd8955dc13bab83afd5f76b81"},
-    {file = "sentencepiece-0.1.99-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ed6ea1819fd612c989999e44a51bf556d0ef6abfb553080b9be3d347e18bcfb7"},
-    {file = "sentencepiece-0.1.99-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a2a0260cd1fb7bd8b4d4f39dc2444a8d5fd4e0a0c4d5c899810ef1abf99b2d45"},
-    {file = "sentencepiece-0.1.99-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8a1abff4d1ff81c77cac3cc6fefa34fa4b8b371e5ee51cb7e8d1ebc996d05983"},
-    {file = "sentencepiece-0.1.99-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:004e6a621d4bc88978eecb6ea7959264239a17b70f2cbc348033d8195c9808ec"},
-    {file = "sentencepiece-0.1.99-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:db361e03342c41680afae5807590bc88aa0e17cfd1a42696a160e4005fcda03b"},
-    {file = "sentencepiece-0.1.99-cp311-cp311-win32.whl", hash = "sha256:2d95e19168875b70df62916eb55428a0cbcb834ac51d5a7e664eda74def9e1e0"},
-    {file = "sentencepiece-0.1.99-cp311-cp311-win_amd64.whl", hash = "sha256:f90d73a6f81248a909f55d8e6ef56fec32d559e1e9af045f0b0322637cb8e5c7"},
-    {file = "sentencepiece-0.1.99-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:62e24c81e74bd87a6e0d63c51beb6527e4c0add67e1a17bac18bcd2076afcfeb"},
-    {file = "sentencepiece-0.1.99-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:57efcc2d51caff20d9573567d9fd3f854d9efe613ed58a439c78c9f93101384a"},
-    {file = "sentencepiece-0.1.99-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6a904c46197993bd1e95b93a6e373dca2f170379d64441041e2e628ad4afb16f"},
-    {file = "sentencepiece-0.1.99-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d89adf59854741c0d465f0e1525b388c0d174f611cc04af54153c5c4f36088c4"},
-    {file = "sentencepiece-0.1.99-cp36-cp36m-win32.whl", hash = "sha256:47c378146928690d1bc106fdf0da768cebd03b65dd8405aa3dd88f9c81e35dba"},
-    {file = "sentencepiece-0.1.99-cp36-cp36m-win_amd64.whl", hash = "sha256:9ba142e7a90dd6d823c44f9870abdad45e6c63958eb60fe44cca6828d3b69da2"},
-    {file = "sentencepiece-0.1.99-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b7b1a9ae4d7c6f1f867e63370cca25cc17b6f4886729595b885ee07a58d3cec3"},
-    {file = "sentencepiece-0.1.99-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d0f644c9d4d35c096a538507b2163e6191512460035bf51358794a78515b74f7"},
-    {file = "sentencepiece-0.1.99-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c8843d23a0f686d85e569bd6dcd0dd0e0cbc03731e63497ca6d5bacd18df8b85"},
-    {file = "sentencepiece-0.1.99-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:33e6f690a1caebb4867a2e367afa1918ad35be257ecdb3455d2bbd787936f155"},
-    {file = "sentencepiece-0.1.99-cp37-cp37m-win32.whl", hash = "sha256:8a321866c2f85da7beac74a824b4ad6ddc2a4c9bccd9382529506d48f744a12c"},
-    {file = "sentencepiece-0.1.99-cp37-cp37m-win_amd64.whl", hash = "sha256:c42f753bcfb7661c122a15b20be7f684b61fc8592c89c870adf52382ea72262d"},
-    {file = "sentencepiece-0.1.99-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:85b476406da69c70586f0bb682fcca4c9b40e5059814f2db92303ea4585c650c"},
-    {file = "sentencepiece-0.1.99-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:cfbcfe13c69d3f87b7fcd5da168df7290a6d006329be71f90ba4f56bc77f8561"},
-    {file = "sentencepiece-0.1.99-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:445b0ec381af1cd4eef95243e7180c63d9c384443c16c4c47a28196bd1cda937"},
-    {file = "sentencepiece-0.1.99-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c6890ea0f2b4703f62d0bf27932e35808b1f679bdb05c7eeb3812b935ba02001"},
-    {file = "sentencepiece-0.1.99-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fb71af492b0eefbf9f2501bec97bcd043b6812ab000d119eaf4bd33f9e283d03"},
-    {file = "sentencepiece-0.1.99-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:27b866b5bd3ddd54166bbcbf5c8d7dd2e0b397fac8537991c7f544220b1f67bc"},
-    {file = "sentencepiece-0.1.99-cp38-cp38-win32.whl", hash = "sha256:b133e8a499eac49c581c3c76e9bdd08c338cc1939e441fee6f92c0ccb5f1f8be"},
-    {file = "sentencepiece-0.1.99-cp38-cp38-win_amd64.whl", hash = "sha256:0eaf3591dd0690a87f44f4df129cf8d05d8a4029b5b6709b489b8e27f9a9bcff"},
-    {file = "sentencepiece-0.1.99-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:38efeda9bbfb55052d482a009c6a37e52f42ebffcea9d3a98a61de7aee356a28"},
-    {file = "sentencepiece-0.1.99-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6c030b081dc1e1bcc9fadc314b19b740715d3d566ad73a482da20d7d46fd444c"},
-    {file = "sentencepiece-0.1.99-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:84dbe53e02e4f8a2e45d2ac3e430d5c83182142658e25edd76539b7648928727"},
-    {file = "sentencepiece-0.1.99-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0b0f55d0a0ee1719b4b04221fe0c9f0c3461dc3dabd77a035fa2f4788eb3ef9a"},
-    {file = "sentencepiece-0.1.99-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:18e800f206cd235dc27dc749299e05853a4e4332e8d3dfd81bf13d0e5b9007d9"},
-    {file = "sentencepiece-0.1.99-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2ae1c40cda8f9d5b0423cfa98542735c0235e7597d79caf318855cdf971b2280"},
-    {file = "sentencepiece-0.1.99-cp39-cp39-win32.whl", hash = "sha256:c84ce33af12ca222d14a1cdd37bd76a69401e32bc68fe61c67ef6b59402f4ab8"},
-    {file = "sentencepiece-0.1.99-cp39-cp39-win_amd64.whl", hash = "sha256:350e5c74d739973f1c9643edb80f7cc904dc948578bcb1d43c6f2b173e5d18dd"},
-    {file = "sentencepiece-0.1.99.tar.gz", hash = "sha256:189c48f5cb2949288f97ccdb97f0473098d9c3dcf5a3d99d4eabe719ec27297f"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:188779e1298a1c8b8253c7d3ad729cb0a9891e5cef5e5d07ce4592c54869e227"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bed9cf85b296fa2b76fc2547b9cbb691a523864cebaee86304c43a7b4cb1b452"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d7b67e724bead13f18db6e1d10b6bbdc454af574d70efbb36f27d90387be1ca3"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2fde4b08cfe237be4484c6c7c2e2c75fb862cfeab6bd5449ce4caeafd97b767a"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4c378492056202d1c48a4979650981635fd97875a00eabb1f00c6a236b013b5e"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1380ce6540a368de2ef6d7e6ba14ba8f3258df650d39ba7d833b79ee68a52040"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-win32.whl", hash = "sha256:a1151d6a6dd4b43e552394aed0edfe9292820272f0194bd56c7c1660a0c06c3d"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:d490142b0521ef22bc1085f061d922a2a6666175bb6b42e588ff95c0db6819b2"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:17982700c4f6dbb55fa3594f3d7e5dd1c8659a274af3738e33c987d2a27c9d5c"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:7c867012c0e8bcd5bdad0f791609101cb5c66acb303ab3270218d6debc68a65e"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7fd6071249c74f779c5b27183295b9202f8dedb68034e716784364443879eaa6"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:27f90c55a65013cbb8f4d7aab0599bf925cde4adc67ae43a0d323677b5a1c6cb"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b293734059ef656dcd65be62ff771507bea8fed0a711b6733976e1ed3add4553"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e58b47f933aca74c6a60a79dcb21d5b9e47416256c795c2d58d55cec27f9551d"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-win32.whl", hash = "sha256:c581258cf346b327c62c4f1cebd32691826306f6a41d8c4bec43b010dee08e75"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:0993dbc665f4113017892f1b87c3904a44d0640eda510abcacdfb07f74286d36"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:ea5f536e32ea8ec96086ee00d7a4a131ce583a1b18d130711707c10e69601cb2"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d0cb51f53b6aae3c36bafe41e86167c71af8370a039f542c43b0cce5ef24a68c"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3212121805afc58d8b00ab4e7dd1f8f76c203ddb9dc94aa4079618a31cf5da0f"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2a3149e3066c2a75e0d68a43eb632d7ae728c7925b517f4c05c40f6f7280ce08"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:632f3594d3e7ac8b367bca204cb3fd05a01d5b21455acd097ea4c0e30e2f63d7"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f295105c6bdbb05bd5e1b0cafbd78ff95036f5d3641e7949455a3f4e5e7c3109"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-win32.whl", hash = "sha256:fb89f811e5efd18bab141afc3fea3de141c3f69f3fe9e898f710ae7fe3aab251"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:7a673a72aab81fef5ebe755c6e0cc60087d1f3a4700835d40537183c1703a45f"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:4547683f330289ec4f093027bfeb87f9ef023b2eb6f879fdc4a8187c7e0ffb90"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7cd6175f7eaec7142d2bf6f6597ce7db4c9ac89acf93fcdb17410c3a8b781eeb"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:859ba1acde782609a0910a26a60e16c191a82bf39b5621107552c0cd79fad00f"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bcbbef6cc277f8f18f36959e305f10b1c620442d75addc79c21d7073ae581b50"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-win32.whl", hash = "sha256:536b934e244829e3fe6c4f198652cd82da48adb9aa145c9f00889542726dee3d"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-win_amd64.whl", hash = "sha256:0a91aaa3c769b52440df56fafda683b3aa48e3f2169cf7ee5b8c8454a7f3ae9b"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:787e480ca4c1d08c9985a7eb1eae4345c107729c99e9b5a9a00f2575fc7d4b4b"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f4d158189eb2ecffea3a51edf6d25e110b3678ec47f1a40f2d541eafbd8f6250"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d1e5ca43013e8935f25457a4fca47e315780172c3e821b4b13a890668911c792"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7140d9e5a74a0908493bb4a13f1f16a401297bd755ada4c707e842fbf6f0f5bf"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-win32.whl", hash = "sha256:6cf333625234f247ab357b0bd9836638405ea9082e1543d5b8408f014979dcbf"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-win_amd64.whl", hash = "sha256:ff88712338b01031910e8e61e7239aff3ce8869ee31a47df63cb38aadd591bea"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:20813a68d4c221b1849c62c30e1281ea81687894d894b8d4a0f4677d9311e0f5"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:926ef920ae2e8182db31d3f5d081ada57804e3e1d3a8c4ef8b117f9d9fb5a945"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:89f65f69636b7e9c015b79dff9c9985a9bc7d19ded6f79ef9f1ec920fdd73ecf"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0f67eae0dbe6f2d7d6ba50a354623d787c99965f068b81e145d53240198021b0"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:98501e075f35dd1a1d5a20f65be26839fcb1938752ec61539af008a5aa6f510b"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e3d1d2cc4882e8d6a1adf9d5927d7716f80617fc693385661caff21888972269"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-win32.whl", hash = "sha256:b99a308a2e5e569031ab164b74e6fab0b6f37dfb493c32f7816225f4d411a6dd"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:cdb701eec783d3ec86b7cd4c763adad8eaf6b46db37ee1c36e5e6c44b3fe1b5f"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:1e0f9c4d0a6b0af59b613175f019916e28ade076e21242fd5be24340d8a2f64a"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:298f21cc1366eb60311aedba3169d30f885c363ddbf44214b0a587d2908141ad"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3f1ec95aa1e5dab11f37ac7eff190493fd87770f7a8b81ebc9dd768d1a3c8704"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7b06b70af54daa4b4904cbb90b4eb6d35c9f3252fdc86c9c32d5afd4d30118d8"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:22e37bac44dd6603388cb598c64ff7a76e41ca774646f21c23aadfbf5a2228ab"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0461324897735512a32d222e3d886e24ad6a499761952b6bda2a9ee6e4313ea5"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-win32.whl", hash = "sha256:38aed822fb76435fa1f12185f10465a94ab9e51d5e8a9159e9a540ce926f0ffd"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:d8cf876516548b5a1d6ac4745d8b554f5c07891d55da557925e5c13ff0b4e6ad"},
+    {file = "sentencepiece-0.2.0.tar.gz", hash = "sha256:a52c19171daaf2e697dc6cbe67684e0fa341b1248966f6aebb541de654d15843"},
 ]
 
 [[package]]
@@ -1194,4 +1201,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9"
-content-hash = "c8c4cc87637266a7b85debcbafa8887c5ad81cc8ef40e98a3f52c7c50af05c03"
+content-hash = "8e03f3a9b833fd86890a318a86d42dc4ca71353bc08af5dffd98efddf59f7e2b"
diff --git a/pyproject.toml b/pyproject.toml
index 25e2e20b24896..07dfbdee784a0 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -17,11 +17,11 @@ classifiers = [
 [tool.poetry.dependencies]
 python = ">=3.9"
 numpy = "^1.25.0"
-sentencepiece = ">=0.1.98,<0.2.0"
 transformers = ">=4.35.2,<5.0.0"
 protobuf = ">=4.21.0,<5.0.0"
 gguf = { path = "./gguf-py" }
 torch = { version = "^2.2.0", source = "pytorch" }
+sentencepiece = "^0.2.0"
 
 [tool.poetry.dev-dependencies]
 pytest = "^5.2"

From fe883305c317779e80c64bb901f14e385be4689e Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Fri, 19 Jul 2024 14:38:17 -0400
Subject: [PATCH 18/19] chore : Add gguf_template to poetry scripts

Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
---
 gguf-py/pyproject.toml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/gguf-py/pyproject.toml b/gguf-py/pyproject.toml
index 471c8aa67af29..4241c5c17cbbb 100644
--- a/gguf-py/pyproject.toml
+++ b/gguf-py/pyproject.toml
@@ -37,3 +37,4 @@ gguf-convert-endian = "scripts:gguf_convert_endian_entrypoint"
 gguf-dump = "scripts:gguf_dump_entrypoint"
 gguf-set-metadata = "scripts:gguf_set_metadata_entrypoint"
 gguf-new-metadata = "scripts:gguf_new_metadata_entrypoint"
+gguf-template = "scripts:gguf_template"

From a083c6cf6d2ac761173287124ee051eb6acc634d Mon Sep 17 00:00:00 2001
From: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
Date: Fri, 19 Jul 2024 14:53:56 -0400
Subject: [PATCH 19/19] chore : Add gguf template entrypoint to scripts sub
 package and fix toml entry

---
 gguf-py/pyproject.toml      | 2 +-
 gguf-py/scripts/__init__.py | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/gguf-py/pyproject.toml b/gguf-py/pyproject.toml
index 4241c5c17cbbb..42c312c8030c2 100644
--- a/gguf-py/pyproject.toml
+++ b/gguf-py/pyproject.toml
@@ -37,4 +37,4 @@ gguf-convert-endian = "scripts:gguf_convert_endian_entrypoint"
 gguf-dump = "scripts:gguf_dump_entrypoint"
 gguf-set-metadata = "scripts:gguf_set_metadata_entrypoint"
 gguf-new-metadata = "scripts:gguf_new_metadata_entrypoint"
-gguf-template = "scripts:gguf_template"
+gguf-template = "scripts:gguf_template_entrypoint"
diff --git a/gguf-py/scripts/__init__.py b/gguf-py/scripts/__init__.py
index e77f2e9c97c31..7d75bae46dfb7 100644
--- a/gguf-py/scripts/__init__.py
+++ b/gguf-py/scripts/__init__.py
@@ -4,3 +4,4 @@
 from .gguf_dump import main as gguf_dump_entrypoint
 from .gguf_set_metadata import main as gguf_set_metadata_entrypoint
 from .gguf_new_metadata import main as gguf_new_metadata_entrypoint
+from .gguf_template import main as gguf_template_entrypoint