Upload folder using huggingface_hub

README.md

@@ -8,7 +8,7 @@ This tiny model is intended for debugging. It is randomly initialized using the
 
 | File path | Size |
 |------|------|
-| model.safetensors | 6.19MB |
+| model.safetensors | 6.2MB |
 
 
 ### Example usage:
@@ -67,6 +67,9 @@ print(output_text)
 
 ### Codes to create this repo:
 
+<details>
+<summary>Python codes</summary>
+
 ```python
 import json
 from pathlib import Path
@@ -174,8 +177,12 @@ replace_file(f'{save_folder}/modeling_kimi_k25.py',
              "")
 ```
 
+</details>
+
 ### Printing the model:
 
+<details><summary>Click to expand</summary>
+
 ```text
 KimiK25ForConditionalGeneration(
   (vision_tower): MoonViT3dPretrainedModel(
@@ -270,4 +277,6 @@ KimiK25ForConditionalGeneration(
     (lm_head): Linear(in_features=8, out_features=163840, bias=False)
   )
 )
-```
+```
+
+</details>

chat_template.jinja

@@ -5,7 +5,7 @@
     {%- elif c is not none -%}
       {% for content in c -%}
         {% if content['type'] == 'image' or content['type'] == 'image_url' -%}
-          <|media_start|>image<|media_content|><|media_pad|><|media_end|>
+          <|media_begin|>image<|media_content|><|media_pad|><|media_end|>
         {% elif content['type'] == 'video' or content['type']== 'video_url'-%}
           <|kimi_k25_video_placeholder|>
         {% else -%}
@@ -57,10 +57,6 @@
     <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
   {%- endif -%}
 {%- endif -%}
-
-{%- if messages|length == 0 or messages[0]['role'] != 'system' -%}
-  <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
-{%- endif -%}
   
 {%- for message in hist_msgs -%}
   {{set_roles(message)}}

tokenization_kimi.py

@@ -8,7 +8,8 @@ from typing import Any, Dict, Iterator, List, Optional, Tuple, Union, cast
 import tiktoken
 from tiktoken.load import load_tiktoken_bpe
 from tokenizers import AddedToken
-from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode
+
+from transformers.convert_slow_tokenizer import bytes_to_unicode
 from transformers.tokenization_utils import PreTrainedTokenizer
 
 from .tool_declaration_ts import encode_tools_to_typescript_style