chat-v1.0.1
Browse files- config.json +2 -2
- model.safetensors +2 -2
- tokenizer.json +2 -2
- tokenizer_config.json +1 -50
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -39,5 +39,5 @@
|
|
39 |
"transformers_version": "4.45.2",
|
40 |
"unsloth_version": "2024.10.3",
|
41 |
"use_cache": true,
|
42 |
-
"vocab_size":
|
43 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/home/mkurman/gitlab/ai/model-trainer/results/llama-2_4b/2024-10-22 20_20_55/final",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
39 |
"transformers_version": "4.45.2",
|
40 |
"unsloth_version": "2024.10.3",
|
41 |
"use_cache": true,
|
42 |
+
"vocab_size": 128256
|
43 |
}
|
model.safetensors
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 sha256:93390ae1e56c8ac5f58a4f83d81c4bb6922f46b8415bfb9c3fcc070039c65118
|
3 |
+
size 4943287208
|
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 sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
3 |
+
size 17209920
|
tokenizer_config.json
CHANGED
@@ -2047,58 +2047,10 @@
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
2050 |
-
},
|
2051 |
-
"128256": {
|
2052 |
-
"content": "</reflection>",
|
2053 |
-
"lstrip": false,
|
2054 |
-
"normalized": true,
|
2055 |
-
"rstrip": false,
|
2056 |
-
"single_word": false,
|
2057 |
-
"special": false
|
2058 |
-
},
|
2059 |
-
"128257": {
|
2060 |
-
"content": "</thinking>",
|
2061 |
-
"lstrip": false,
|
2062 |
-
"normalized": true,
|
2063 |
-
"rstrip": false,
|
2064 |
-
"single_word": false,
|
2065 |
-
"special": false
|
2066 |
-
},
|
2067 |
-
"128258": {
|
2068 |
-
"content": "<reflection>",
|
2069 |
-
"lstrip": false,
|
2070 |
-
"normalized": true,
|
2071 |
-
"rstrip": false,
|
2072 |
-
"single_word": false,
|
2073 |
-
"special": false
|
2074 |
-
},
|
2075 |
-
"128259": {
|
2076 |
-
"content": "</output>",
|
2077 |
-
"lstrip": false,
|
2078 |
-
"normalized": true,
|
2079 |
-
"rstrip": false,
|
2080 |
-
"single_word": false,
|
2081 |
-
"special": false
|
2082 |
-
},
|
2083 |
-
"128260": {
|
2084 |
-
"content": "<output>",
|
2085 |
-
"lstrip": false,
|
2086 |
-
"normalized": true,
|
2087 |
-
"rstrip": false,
|
2088 |
-
"single_word": false,
|
2089 |
-
"special": false
|
2090 |
-
},
|
2091 |
-
"128261": {
|
2092 |
-
"content": "<thinking>",
|
2093 |
-
"lstrip": false,
|
2094 |
-
"normalized": true,
|
2095 |
-
"rstrip": false,
|
2096 |
-
"single_word": false,
|
2097 |
-
"special": false
|
2098 |
}
|
2099 |
},
|
2100 |
"bos_token": "<|begin_of_text|>",
|
2101 |
-
"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
|
2102 |
"clean_up_tokenization_spaces": true,
|
2103 |
"eos_token": "<|eot_id|>",
|
2104 |
"model_input_names": [
|
@@ -2106,6 +2058,5 @@
|
|
2106 |
"attention_mask"
|
2107 |
],
|
2108 |
"model_max_length": 131072,
|
2109 |
-
"pad_token": "<|finetune_right_pad_id|>",
|
2110 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2111 |
}
|
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"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",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"model_input_names": [
|
|
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 131072,
|
|
|
2061 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2062 |
}
|