Fix UTF-8 handling (including colors) (ggml-org#79)

CCLDArjun · Mar 13, 2023 · 2a20f48 · 2a20f48
1 parent d1f2247
commit 2a20f48
Show file tree

Hide file tree

Showing 2 changed files with 27 additions and 11 deletions.
diff --git a/convert-pth-to-ggml.py b/convert-pth-to-ggml.py
@@ -22,7 +22,6 @@
 import struct
 import numpy as np
 import torch
-
 from sentencepiece import SentencePieceProcessor
 
 if len(sys.argv) < 3:
@@ -101,12 +100,28 @@ def get_n_parts(dim):
 
     # Is this correct??
     for i in range(32000):
-        # TODO: this is probably wrong - not sure how this tokenizer works
-        text = tokenizer.decode([29889, i]).encode('utf-8')
-        # remove the first byte (it's always '.')
-        text = text[1:]
-        fout.write(struct.pack("i", len(text)))
-        fout.write(text)
+        if tokenizer.is_unknown(i):
+            # "<unk>" token (translated as ??)
+            text = " \u2047 ".encode("utf-8")
+            fout.write(struct.pack("i", len(text)))
+            fout.write(text)
+        elif tokenizer.is_control(i):
+            # "<s>"/"</s>" tokens
+            fout.write(struct.pack("i", 0))
+        elif tokenizer.is_byte(i):
+            # "<U+XX>" tokens (which may be invalid UTF-8)
+            piece = tokenizer.id_to_piece(i)
+            if len(piece) != 6:
+                print("Invalid token: " + piece)
+                sys.exit(1)
+            byte_value = int(piece[3:-1], 16)
+            fout.write(struct.pack("i", 1))
+            fout.write(struct.pack("B", byte_value))
+        else:
+            # normal token. Uses U+2581 (LOWER ONE EIGHTH BLOCK) to represent spaces.
+            text = tokenizer.id_to_piece(i).replace("\u2581", " ").encode("utf-8")
+            fout.write(struct.pack("i", len(text)))
+            fout.write(text)
 
     for k, v in model.items():
         name = k

diff --git a/main.cpp b/main.cpp
@@ -939,17 +939,18 @@ int main(int argc, char ** argv) {
                     break;
                 }
             }
+
+            // reset color to default if we there is no pending user input
+            if (!input_noecho && params.use_color && embd_inp.size() == input_consumed) {
+                printf(ANSI_COLOR_RESET);
+            }
         }
 
         // display text
         if (!input_noecho) {
             for (auto id : embd) {
                 printf("%s", vocab.id_to_token[id].c_str());
             }
-            // reset color to default if we there is no pending user input
-            if (params.use_color && embd_inp.size() <= input_consumed) {
-                printf(ANSI_COLOR_RESET);
-            }
             fflush(stdout);
         }