Upload folder using huggingface_hub

added_tokens.json

@@ -1,8 +1,3 @@
 {
-  "</s>": 20001,
-  "<s>": 20000,
-  "<|end_header_id|>": 20003,
-  "<|eom_id|>": 20004,
-  "<|eot_id|>": 20005,
-  "<|start_header_id|>": 20002
+  "</s>": 19999
 }

config.json

@@ -29,5 +29,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.1",
   "use_cache": true,
-  "vocab_size": 20032
+  "vocab_size": 20000
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad51782a40518730fd9970ccf9c9c2709170d6059c4ce5a728cad970c4305296
-size 1989418512
+oid sha256:cdf97b27df4f3be4003f6272cf388d438aa4b682874a3194142a836b6ccf4e18
+size 1989271056

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67135bd6c8a4eb112ec85adb854be689560f9a8321c73020ee526919cb6f09cb
+oid sha256:e1dccbf834ff6ff6a08c9d69c3e9916ab875d1c33ee505561736279ca5a1c828
 size 1996220256

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d171150a5e34f6f9434a7eb112b03f7eb4259ae81478e7e7ee045ee9e1822aad
-size 248045512
+oid sha256:3879139496cf09782a4ff60ab9dced82a5db1a74a2c09f5b15e8fa56b8d9f4ad
+size 247898056

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 4233650688
+    "total_size": 4233355776
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",

special_tokens_map.json

@@ -1,19 +1,34 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": {
-    "content": "<|begin_of_text|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|eot_id|>",
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|eot_id|>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -14,7 +14,7 @@
     },
     {
       "id": 1,
-      "content": "<|begin_of_text|>",
+      "content": "<s>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -23,7 +23,7 @@
     },
     {
       "id": 2,
-      "content": "<|end_of_text|>",
+      "content": "</s>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -217,7 +217,7 @@
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
-      "special": false
+      "special": true
     },
     {
       "id": 24,
@@ -226,7 +226,7 @@
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
-      "special": false
+      "special": true
     },
     {
       "id": 25,
@@ -344,60 +344,6 @@
       "rstrip": false,
       "normalized": false,
       "special": false
-    },
-    {
-      "id": 20000,
-      "content": "<s>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 20001,
-      "content": "</s>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 20002,
-      "content": "<|start_header_id|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 20003,
-      "content": "<|end_header_id|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 20004,
-      "content": "<|eom_id|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 20005,
-      "content": "<|eot_id|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {
@@ -418,7 +364,7 @@
     "single": [
       {
         "SpecialToken": {
-          "id": "<|begin_of_text|>",
+          "id": "<s>",
           "type_id": 0
         }
       },
@@ -430,7 +376,7 @@
       },
       {
         "SpecialToken": {
-          "id": "<|end_of_text|>",
+          "id": "</s>",
           "type_id": 0
         }
       }
@@ -438,7 +384,7 @@
     "pair": [
       {
         "SpecialToken": {
-          "id": "<|begin_of_text|>",
+          "id": "<s>",
           "type_id": 0
         }
       },
@@ -450,13 +396,13 @@
       },
       {
         "SpecialToken": {
-          "id": "<|end_of_text|>",
+          "id": "</s>",
           "type_id": 0
         }
       },
       {
         "SpecialToken": {
-          "id": "<|begin_of_text|>",
+          "id": "<s>",
           "type_id": 1
         }
       },
@@ -468,28 +414,28 @@
       },
       {
         "SpecialToken": {
-          "id": "<|end_of_text|>",
+          "id": "</s>",
           "type_id": 1
         }
       }
     ],
     "special_tokens": {
-      "<|begin_of_text|>": {
-        "id": "<|begin_of_text|>",
+      "</s>": {
+        "id": "</s>",
         "ids": [
-          1
+          2
         ],
         "tokens": [
-          "<|begin_of_text|>"
+          "</s>"
         ]
       },
-      "<|end_of_text|>": {
-        "id": "<|end_of_text|>",
+      "<s>": {
+        "id": "<s>",
         "ids": [
-          2
+          1
         ],
         "tokens": [
-          "<|end_of_text|>"
+          "<s>"
         ]
       }
     }
@@ -523,8 +469,8 @@
     "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
-      "<|begin_of_text|>": 1,
-      "<|end_of_text|>": 2,
+      "<s>": 1,
+      "</s>": 2,
       "<pad>": 3,
       "▁▁": 4,
       "▁▁▁": 5,

tokenizer_config.json

@@ -12,7 +12,7 @@
       "special": true
     },
     "1": {
-      "content": "<|begin_of_text|>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -20,7 +20,7 @@
       "special": true
     },
     "2": {
-      "content": "<|end_of_text|>",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -193,7 +193,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "24": {
       "content": "<|im_end|>",
@@ -201,7 +201,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "25": {
       "content": "<|system|>",
@@ -306,63 +306,18 @@
       "rstrip": false,
       "single_word": false,
       "special": false
-    },
-    "20000": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "20001": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "20002": {
-      "content": "<|start_header_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "20003": {
-      "content": "<|end_header_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "20004": {
-      "content": "<|eom_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "20005": {
-      "content": "<|eot_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "bos_token": "<|begin_of_text|>",
-  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
+  "additional_special_tokens": [
+    "<|im_start|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|eot_id|>",
+  "pad_token": "<pad>",
   "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,