py : add Phi-1.5/Phi-2 tokenizer (#9361)

* add phi2 tokenizer

* add phi name to convert_hf_to_gguf_update.py

* make tokenizer_pre consistent; llama.cpp work

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index f02c65026e0a691b877f16c11d64b38a2c738229..01a8a50a27cc630fed36a89866b395393bd0b777 100755 (executable)
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -626,6 +626,9 @@ class Model:
         if chkhsh == "4e2b24cc4770243d65a2c9ec19770a72f08cffc161adbb73fcbb6b7dd45a0aae":
             # ref: https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct
             res = "exaone"
+        if chkhsh == "fcace8b9cac38ce847670c970cd5892031a753a1ef381abd1d9af00f713da085":
+            # ref: https://huggingface.co/microsoft/phi-2
+            res = "phi-2"
 
         if res is None:
             logger.warning("\n")

diff --git a/convert_hf_to_gguf_update.py b/convert_hf_to_gguf_update.py
index 59a0b81a188807009694ccad2fe0eeeafb4fb26f..021f65abdc45d12f0f792f97d3a0be21e409c6fd 100755 (executable)
--- a/convert_hf_to_gguf_update.py
+++ b/convert_hf_to_gguf_update.py
@@ -98,6 +98,7 @@ models = [
     {'name': "bloom",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigscience/bloom", },
     {'name': "gpt3-finnish",   "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/TurkuNLP/gpt3-finnish-small", },
     {"name": "exaone",         "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct", },
+    {"name": "phi-2",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/microsoft/phi-2", },
 ]