Upload 5 files
Browse files- generation_config.json +1 -8
- special_tokens_map.json +1 -16
- tokenizer.json +2 -2
- tokenizer_config.json +6 -14
generation_config.json
CHANGED
@@ -1,13 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"do_sample": true,
|
4 |
"bos_token_id": 128000,
|
5 |
-
"eos_token_id":
|
6 |
-
128001,
|
7 |
-
128008,
|
8 |
-
128009
|
9 |
-
],
|
10 |
-
"temperature": 0.6,
|
11 |
-
"top_p": 0.9,
|
12 |
"transformers_version": "4.45.0.dev0"
|
13 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
|
|
3 |
"bos_token_id": 128000,
|
4 |
+
"eos_token_id": 128001,
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"transformers_version": "4.45.0.dev0"
|
6 |
}
|
special_tokens_map.json
CHANGED
@@ -1,12 +1,4 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
"<thinking>",
|
4 |
-
"</thinking>",
|
5 |
-
"<output>",
|
6 |
-
"</output>",
|
7 |
-
"<reflection>",
|
8 |
-
"</reflection>"
|
9 |
-
],
|
10 |
"bos_token": {
|
11 |
"content": "<|begin_of_text|>",
|
12 |
"lstrip": false,
|
@@ -15,14 +7,7 @@
|
|
15 |
"single_word": false
|
16 |
},
|
17 |
"eos_token": {
|
18 |
-
"content": "<|
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
},
|
24 |
-
"pad_token": {
|
25 |
-
"content": "<|eot_id|>",
|
26 |
"lstrip": false,
|
27 |
"normalized": false,
|
28 |
"rstrip": false,
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<|begin_of_text|>",
|
4 |
"lstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|end_of_text|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
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 sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4
|
3 |
+
size 9085657
|
tokenizer_config.json
CHANGED
@@ -2001,7 +2001,7 @@
|
|
2001 |
"special": true
|
2002 |
},
|
2003 |
"128250": {
|
2004 |
-
"content": "
|
2005 |
"lstrip": false,
|
2006 |
"normalized": false,
|
2007 |
"rstrip": false,
|
@@ -2009,7 +2009,7 @@
|
|
2009 |
"special": true
|
2010 |
},
|
2011 |
"128251": {
|
2012 |
-
"content": "
|
2013 |
"lstrip": false,
|
2014 |
"normalized": false,
|
2015 |
"rstrip": false,
|
@@ -2017,7 +2017,7 @@
|
|
2017 |
"special": true
|
2018 |
},
|
2019 |
"128252": {
|
2020 |
-
"content": "
|
2021 |
"lstrip": false,
|
2022 |
"normalized": false,
|
2023 |
"rstrip": false,
|
@@ -2025,7 +2025,7 @@
|
|
2025 |
"special": true
|
2026 |
},
|
2027 |
"128253": {
|
2028 |
-
"content": "
|
2029 |
"lstrip": false,
|
2030 |
"normalized": false,
|
2031 |
"rstrip": false,
|
@@ -2033,7 +2033,7 @@
|
|
2033 |
"special": true
|
2034 |
},
|
2035 |
"128254": {
|
2036 |
-
"content": "
|
2037 |
"lstrip": false,
|
2038 |
"normalized": false,
|
2039 |
"rstrip": false,
|
@@ -2041,7 +2041,7 @@
|
|
2041 |
"special": true
|
2042 |
},
|
2043 |
"128255": {
|
2044 |
-
"content": "
|
2045 |
"lstrip": false,
|
2046 |
"normalized": false,
|
2047 |
"rstrip": false,
|
@@ -2056,14 +2056,6 @@
|
|
2056 |
"input_ids",
|
2057 |
"attention_mask"
|
2058 |
],
|
2059 |
-
"additional_special_tokens": [
|
2060 |
-
"<thinking>",
|
2061 |
-
"</thinking>",
|
2062 |
-
"<output>",
|
2063 |
-
"</output>",
|
2064 |
-
"<reflection>",
|
2065 |
-
"</reflection>"
|
2066 |
-
],
|
2067 |
"model_max_length": 131072,
|
2068 |
"pad_token": "<|eot_id|>",
|
2069 |
"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 {%- set date_string = \"26 Jul 2024\" %}\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 + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\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 {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\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",
|
|
|
2001 |
"special": true
|
2002 |
},
|
2003 |
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
"lstrip": false,
|
2006 |
"normalized": false,
|
2007 |
"rstrip": false,
|
|
|
2009 |
"special": true
|
2010 |
},
|
2011 |
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
"lstrip": false,
|
2014 |
"normalized": false,
|
2015 |
"rstrip": false,
|
|
|
2017 |
"special": true
|
2018 |
},
|
2019 |
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
"lstrip": false,
|
2022 |
"normalized": false,
|
2023 |
"rstrip": false,
|
|
|
2025 |
"special": true
|
2026 |
},
|
2027 |
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
"lstrip": false,
|
2030 |
"normalized": false,
|
2031 |
"rstrip": false,
|
|
|
2033 |
"special": true
|
2034 |
},
|
2035 |
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
"lstrip": false,
|
2038 |
"normalized": false,
|
2039 |
"rstrip": false,
|
|
|
2041 |
"special": true
|
2042 |
},
|
2043 |
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
"lstrip": false,
|
2046 |
"normalized": false,
|
2047 |
"rstrip": false,
|
|
|
2056 |
"input_ids",
|
2057 |
"attention_mask"
|
2058 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2059 |
"model_max_length": 131072,
|
2060 |
"pad_token": "<|eot_id|>",
|
2061 |
"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 {%- set date_string = \"26 Jul 2024\" %}\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 + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\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 {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\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",
|