Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +15 -16
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a29c2a38c962b724abf8c63045663798107925b1d9d1ab814d2b16a23f4a8c9
|
| 3 |
+
size 11418677
|
tokenizer_config.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
-
"
|
| 12 |
"content": "user",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": true,
|
|
@@ -16,7 +16,7 @@
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": false
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
"content": "system",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": true,
|
|
@@ -24,6 +24,14 @@
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": false
|
| 26 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"127900": {
|
| 28 |
"content": "<think>",
|
| 29 |
"lstrip": false,
|
|
@@ -57,14 +65,6 @@
|
|
| 57 |
"special": false
|
| 58 |
},
|
| 59 |
"127904": {
|
| 60 |
-
"content": "assistant",
|
| 61 |
-
"lstrip": false,
|
| 62 |
-
"normalized": true,
|
| 63 |
-
"rstrip": false,
|
| 64 |
-
"single_word": false,
|
| 65 |
-
"special": false
|
| 66 |
-
},
|
| 67 |
-
"127905": {
|
| 68 |
"content": "BiBo",
|
| 69 |
"lstrip": false,
|
| 70 |
"normalized": true,
|
|
@@ -72,7 +72,7 @@
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": false
|
| 74 |
},
|
| 75 |
-
"
|
| 76 |
"content": "aloobun",
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": true,
|
|
@@ -80,7 +80,7 @@
|
|
| 80 |
"single_word": false,
|
| 81 |
"special": false
|
| 82 |
},
|
| 83 |
-
"
|
| 84 |
"content": "LowIQGenAI",
|
| 85 |
"lstrip": false,
|
| 86 |
"normalized": true,
|
|
@@ -88,7 +88,7 @@
|
|
| 88 |
"single_word": false,
|
| 89 |
"special": false
|
| 90 |
},
|
| 91 |
-
"
|
| 92 |
"content": "IndieTechie",
|
| 93 |
"lstrip": false,
|
| 94 |
"normalized": true,
|
|
@@ -96,7 +96,7 @@
|
|
| 96 |
"single_word": false,
|
| 97 |
"special": false
|
| 98 |
},
|
| 99 |
-
"
|
| 100 |
"content": "Swamy",
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": true,
|
|
@@ -104,7 +104,7 @@
|
|
| 104 |
"single_word": false,
|
| 105 |
"special": false
|
| 106 |
},
|
| 107 |
-
"
|
| 108 |
"content": "AdarshXs",
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": true,
|
|
@@ -113,7 +113,6 @@
|
|
| 113 |
"special": false
|
| 114 |
}
|
| 115 |
},
|
| 116 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 117 |
"clean_up_tokenization_spaces": false,
|
| 118 |
"eos_token": "<|endoftext|>",
|
| 119 |
"extra_special_tokens": {},
|
|
|
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
+
"3802": {
|
| 12 |
"content": "user",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": true,
|
|
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": false
|
| 18 |
},
|
| 19 |
+
"4535": {
|
| 20 |
"content": "system",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": true,
|
|
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": false
|
| 26 |
},
|
| 27 |
+
"116061": {
|
| 28 |
+
"content": "assistant",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
"127900": {
|
| 36 |
"content": "<think>",
|
| 37 |
"lstrip": false,
|
|
|
|
| 65 |
"special": false
|
| 66 |
},
|
| 67 |
"127904": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
"content": "BiBo",
|
| 69 |
"lstrip": false,
|
| 70 |
"normalized": true,
|
|
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": false
|
| 74 |
},
|
| 75 |
+
"127905": {
|
| 76 |
"content": "aloobun",
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": true,
|
|
|
|
| 80 |
"single_word": false,
|
| 81 |
"special": false
|
| 82 |
},
|
| 83 |
+
"127906": {
|
| 84 |
"content": "LowIQGenAI",
|
| 85 |
"lstrip": false,
|
| 86 |
"normalized": true,
|
|
|
|
| 88 |
"single_word": false,
|
| 89 |
"special": false
|
| 90 |
},
|
| 91 |
+
"127907": {
|
| 92 |
"content": "IndieTechie",
|
| 93 |
"lstrip": false,
|
| 94 |
"normalized": true,
|
|
|
|
| 96 |
"single_word": false,
|
| 97 |
"special": false
|
| 98 |
},
|
| 99 |
+
"127908": {
|
| 100 |
"content": "Swamy",
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": true,
|
|
|
|
| 104 |
"single_word": false,
|
| 105 |
"special": false
|
| 106 |
},
|
| 107 |
+
"127909": {
|
| 108 |
"content": "AdarshXs",
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": true,
|
|
|
|
| 113 |
"special": false
|
| 114 |
}
|
| 115 |
},
|
|
|
|
| 116 |
"clean_up_tokenization_spaces": false,
|
| 117 |
"eos_token": "<|endoftext|>",
|
| 118 |
"extra_special_tokens": {},
|