Upload folder using huggingface_hub

chat_template.jinja

@@ -7,7 +7,7 @@
 
 ## {{ function.name }}
 
-{{ function | tojson(indent=4, ensure_ascii=False) }}
+{{ function | tojson(indent=4)|string }}
 在调用上述函数时，请使用 Json 格式表示调用的参数。
 {%- endfor %}
 {%- endif -%}

config.json

@@ -19,13 +19,14 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 40,
   "num_key_value_heads": 2,
-  "pad_token_id": 151329,
+  "pad_token_id": 151330,
   "partial_rotary_factor": 0.5,
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.52.0.dev0",
+  "transformers_version": "4.52.4",
+  "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 151552
-}
+}

special_tokens_map.json

@@ -16,14 +16,14 @@
     "<|end_of_video|>"
   ],
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|user|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "[MASK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -129,7 +129,7 @@
     "<|begin_of_video|>",
     "<|end_of_video|>"
   ],
-  "chat_template": "[gMASK]<sop>{%- if tools -%}<|system|>\n# 可用工具\n{% for tool in tools %}{%- set function = tool.function if tool.get(\"function\") else tool %}\n\n## {{ function.name }}\n\n{{ function | tojson(indent=4, ensure_ascii=False) }}\n在调用上述函数时，请使用 Json 格式表示调用的参数。{%- endfor %}{%- endif -%}{%- for msg in messages %}{%- if msg.role == 'system' %}<|system|>\n{{ msg.content }}{%- endif %}{%- endfor %}{%- for message in messages if message.role != 'system' %}{%- set role = message['role'] %}{%- set content = message['content'] %}{%- set meta = message.get(\"metadata\", \"\") %}{%- if role == 'user' %}<|user|>\n{{ content }}{%- elif role == 'assistant' and not meta %}<|assistant|>\n{{ content }}{%- elif role == 'assistant' and meta %}<|assistant|>{{ meta }} \n{{ content }}{%- elif role == 'observation' %}<|observation|>\n{{ content }}{%- endif %}{%- endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
+  "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "do_lower_case": false,
   "eos_token": "<|user|>",
@@ -138,9 +138,11 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 128000,
-  "pad_token": "<|endoftext|>",
+  "model_max_length": 32768,
+  "pad_token": "[MASK]",
   "padding_side": "left",
   "remove_space": false,
-  "tokenizer_class": "PreTrainedTokenizer"
-}
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null,
+  "chat_template": "[gMASK]<sop>\n{%- if tools -%}\n<|system|>\n# 可用工具\n{% for tool in tools %}\n    {%- set function = tool.function if tool.get(\"function\") else tool %}\n\n## {{ function.name }}\n\n{{ function | tojson(indent=4)|string }}\n在调用上述函数时，请使用 Json 格式表示调用的参数。\n{%- endfor %}\n{%- endif -%}\n\n{%- for msg in messages %}\n    {%- if msg.role == 'system' %}\n<|system|>\n{{ msg.content }}\n    {%- endif %}\n{%- endfor %}\n\n{%- for message in messages if message.role != 'system' %}\n    {%- set role = message['role'] %}\n    {%- set content = message['content'] %}\n    {%- set meta = message.get(\"metadata\", \"\") %}\n\n    {%- if role == 'user' %}\n<|user|>\n{{ content }}\n    {%- elif role == 'assistant' and not meta %}\n<|assistant|>\n{{ content }}\n    {%- elif role == 'assistant' and meta %}\n<|assistant|>{{ meta }}\n{{ content }}\n    {%- elif role == 'observation' %}\n<|observation|>\n{{ content }}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}<|assistant|>{% endif %}"
+}