Upload tokenizer

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "<beginning_of_sentence>": 200019,
+  "<code_interpreter>": 200023,
+  "<commit_after>": 200018,
+  "<commit_before>": 200016,
+  "<commit_msg>": 200017,
+  "<empty_output>": 200015,
+  "<end_of_document>": 200021,
+  "<end_of_sentence>": 200020,
+  "<filename>": 200006,
+  "<fim_middle>": 200002,
+  "<fim_pad>": 200004,
+  "<fim_prefix>": 200001,
+  "<fim_suffix>": 200003,
+  "<function_call>": 200022,
+  "<gh_stars>": 200007,
+  "<image>": 200025,
+  "<issue_closed>": 200010,
+  "<issue_comment>": 200009,
+  "<issue_start>": 200008,
+  "<jupyter_code>": 200013,
+  "<jupyter_output>": 200014,
+  "<jupyter_start>": 200011,
+  "<jupyter_text>": 200012,
+  "<pad>": 200000,
+  "<reponame>": 200005,
+  "<speech>": 200024
+}

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if message['role'] == 'system' %}{{ '<beginning_of_sentence>system ai_setting=assistant\n' + message['content'][0]['text'] + '<end_of_sentence>\n'}}{% elif message['role'] == 'user' %}{{ '<beginning_of_sentence>user name=user\n' + message['content'][0]['text'] + '<end_of_sentence>\n'}}{% elif message['role'] == 'assistant' %}{{ '<beginning_of_sentence>ai name=assistant\n' }}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{{ '<end_of_sentence>\n' }}{% elif message['role'] == 'function' %}{{ '<beginning_of_sentence>system function_response=functions\n' + '{"name": "' + message['name'] + '", "response": ' + message['content'][0]['text'] + '}' + '<end_of_sentence>\n'}}{% endif %}{% endfor %}{% if tools %}{% for function in tools %}{{ '<beginning_of_sentence>system function_setting=functions\n' + function | tojson + '<end_of_sentence>\n'}}{% endfor %}{% endif %}{% if add_generation_prompt %}{{ '<beginning_of_sentence>ai name=assistant\n' }}{% endif %}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<beginning_of_sentence>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<end_of_sentence>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<end_of_document>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f1dae4255c64e82607c0aaeccf332a3e11c730957ad6fe732a05d099a89791
+size 15517439

tokenizer_config.json

@@ -0,0 +1,220 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "200000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200001": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200002": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200003": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200004": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200005": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200006": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200007": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200008": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200009": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200012": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200013": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200014": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200015": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200016": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200017": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<beginning_of_sentence>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<end_of_sentence>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<end_of_document>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<function_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<code_interpreter>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200024": {
+      "content": "<speech>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200025": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<beginning_of_sentence>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<end_of_sentence>",
+  "extra_special_tokens": {},
+  "model_max_length": 40960000,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<end_of_document>"
+}