From dc07dc492ef9640bbb82904d7c7679f7bdcf6d76 Mon Sep 17 00:00:00 2001
From: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
Date: Wed, 30 Aug 2023 02:25:50 -0600
Subject: convert : various script cleanups/fixes + merges and special token
 handling (#2842)

* convert: Fix permute calls and method/func definitions

* Cleanups for gguf-py

* Minor types cleanups.

* Initial implementation of handling merges and special tokens

* convert: Handle special tokens and merges in vocab only mode

convert: Vocab only mode no longer requires loading model tensors

* gguf: Refactor tensor name mapping

* convert: Fix type hint for special_token_types in SpecialVocab

* Use common special vocab handling in various conversion scripts

* First pass at implementing suggested changes

* Second pass

* gguf: SpecialVocab: Fix issue with special token content not in a dict

gguf: SpecialVocab: Allow skipping handling of merges

* convert-falcon-hf-to-gguf: Support --vocab-only option, bail out if no tokenizer.json

* convert-gptneox-hf-to-gguf and convert: Only handle merges for BPE tokenizer

* gguf: SpecialVocab: Actually set load_merges in object

* Uniform args parsing and vocab only mode for convert examples

* convert.py: Set gpt2 as tokenizer model when using BPE

* Squish last type warning in gguf.py - yay!
---
 convert-lora-to-ggml.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'convert-lora-to-ggml.py')

diff --git a/convert-lora-to-ggml.py b/convert-lora-to-ggml.py
index a94a7d0a..a00339b4 100755
--- a/convert-lora-to-ggml.py
+++ b/convert-lora-to-ggml.py
@@ -4,7 +4,7 @@ import os
 import re
 import struct
 import sys
-from typing import Any, Dict, Sequence, TextIO
+from typing import Any, Dict, Sequence, BinaryIO
 
 import numpy as np
 import torch
@@ -46,7 +46,7 @@ def translate_tensor_name(t: str) -> str:
         sys.exit(1)
 
 
-def write_file_header(fout: TextIO, params: Dict[str, Any]) -> None:
+def write_file_header(fout: BinaryIO, params: Dict[str, Any]) -> None:
     fout.write(b"ggla"[::-1])  # magic (ggml lora)
     fout.write(struct.pack("i", 1))  # file version
     fout.write(struct.pack("i", params["r"]))
@@ -60,7 +60,7 @@ def write_file_header(fout: TextIO, params: Dict[str, Any]) -> None:
 
 
 def write_tensor_header(
-    self, name: str, shape: Sequence[int], data_type: np.dtype
+    self, name: str, shape: Sequence[int], data_type: np.dtype[Any]
 ) -> None:
     sname = name.encode("utf-8")
     fout.write(
-- 
cgit v1.2.3