llama : more tokenizer fixes (#2810)

* tests : write a Python tokenizer test (wip)

* llama : prefix input text for tokenization with whitespace

* llama : distinguish pieces from decoded text + fix detokenization

* common : add comments

* examples : no longer manually add leading space when tokenizing

* tests : use Python to generate tokenizer tests for C++

* tests : add option to tokenize text files

ggml-ci

* tests : add test-tokenizer-1.py

* llama.cpp : fix LF token

* hellaswag : move the concat space for clarity

* tests : add falcon tests (py + cpp, currently do not pass Unicode)

ggml-ci

* common : temporary separate llama_detokenize calls for SPM and BPE

---------

Co-authored-by: klosax <131523366+klosax@users.noreply.github.com>

1 files changed, 95 insertions, 0 deletions

diff --git a/tests/test-tokenizer-0-llama.py b/tests/test-tokenizer-0-llama.py
new file mode 100644
index 00000000..bc164ee2
--- /dev/null
+++ b/tests/test-tokenizer-0-llama.py
@@ -0,0 +1,95 @@
+# tests with SPM tokenizer
+
+import os
+import sys
+import argparse
+
+from sentencepiece import SentencePieceProcessor
+
+parser = argparse.ArgumentParser()
+parser.add_argument("dir_tokenizer", help="directory containing 'tokenizer.model' file")
+parser.add_argument("--fname-tok",   help="path to a text file to tokenize")
+args = parser.parse_args()
+
+dir_tokenizer = args.dir_tokenizer
+
+tokenizer = SentencePieceProcessor(dir_tokenizer + '/tokenizer.model')
+
+tests = [
+        "",
+        " ",
+        "  ",
+        "   ",
+        "\t",
+        "\n",
+        "\t\n",
+        "Hello world",
+        " Hello world",
+        "Hello World",
+        " Hello World",
+        " Hello World!",
+        "Hello, world!",
+        " Hello, world!",
+        " this is 🦙.cpp",
+        "w048 7tuijk dsdfhu",
+        "нещо на Български",
+        "កាន់តែពិសេសអាចខលចេញ",
+        "🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)",
+        "Hello",
+        " Hello",
+        "  Hello",
+        "   Hello",
+        "    Hello",
+        "    Hello\n    Hello",
+    ]
+
+
+for text in tests:
+    print('text: ', text)
+    print('\nwith bos:')
+    print(tokenizer.encode(text, add_bos=True))
+    print(tokenizer.decode(tokenizer.encode(text, add_bos=True)))
+    print('\nwithout bos:')
+    print(tokenizer.encode(text, add_bos=False))
+    print(tokenizer.decode(tokenizer.encode(text, add_bos=False)))
+
+print("'" + tokenizer.id_to_piece(15043) + "'") # '_Hello'
+print("'" + tokenizer.id_to_piece(29871) + "'") # '_'
+print("'" + tokenizer.decode([15043]) + "'")        # 'Hello'
+print("'" + tokenizer.decode([15043, 15043]) + "'") # 'Hello Hello'
+print("'" + tokenizer.decode([29871, 15043]) + "'")               # ' Hello'
+print("'" + tokenizer.decode([29871, 15043, 29871, 15043]) + "'") # ' Hello  Hello'
+
+print("\n\ntests for C++:\n")
+for text in tests:
+    res = tokenizer.encode(text, add_bos=False)
+
+    k = text.replace('\n', '\\n')
+    k = k.replace('\t', '\\t')
+    k = '"' + k + '"'
+    print("{ %-24s, { " % k, end='')
+    for x in res:
+        print("%7d," % x, end='')
+    print(" }, },")
+
+print(tokenizer.encode('hello'))
+print(tokenizer.encode('world'))
+print(tokenizer.encode(' world'))
+print(tokenizer.encode('hello world'))
+
+fname_tok = args.fname_tok
+if fname_tok:
+    print('tokenizing file: ', fname_tok)
+    fname_out = fname_tok + '.tok'
+    with open(fname_tok, 'r') as f:
+        lines = f.readlines()
+        s = ''.join(lines)
+        res = tokenizer.encode(s, add_bos=True)
+        # write to file
+        with open(fname_out, 'w') as f:
+            for x in res:
+                f.write(str(x) + ' ')
+            f.write('\n')
+        print('len(res): ', len(res))
+        print('len(lines): ', len(lines))
+    print('results written to: ', fname_out)