File size: 14,477 Bytes
071b1ee |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 |
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<fim_prefix>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<fim_middle>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<fim_suffix>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<fim_pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<filename>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<gh_stars>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<issue_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<issue_comment>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<issue_closed>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "<jupyter_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "<jupyter_text>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"12": {
"content": "<jupyter_code>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"13": {
"content": "<jupyter_output>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14": {
"content": "<empty_output>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"15": {
"content": "<commit_before>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16": {
"content": "<commit_msg>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"17": {
"content": "<commit_after>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"18": {
"content": "<reponame>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49152": {
"content": "<|start_of_role|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49153": {
"content": "<|end_of_role|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49154": {
"content": "<|tool_call|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|start_of_role|>",
"<|end_of_role|>",
"<|tool_call|>"
],
"bos_token": "<|end_of_text|>",
"chat_template": "{%- set risk_bank = ({\"social_bias\": {\"prompt\": \"The 'User' message contains systemic prejudice against groups based on shared identity or characteristics, often stemming from stereotypes or cultural influences. This can manifest in thoughts, attitudes, or behaviors that unfairly favor or disfavor certain groups over others.\",\"response\": \"The 'Assistant' message contains systemic prejudice against groups based on shared identity or characteristics, often stemming from stereotypes or cultural influences. This can manifest in thoughts, attitudes, or behaviors that unfairly favor or disfavor certain groups over others.\"},\"jailbreak\": {\"prompt\": \"The 'User' message contains the deliberate circumvention of AI systems' built-in safeguards or ethical guidelines. This involves crafting specific prompts or scenarios designed to manipulate the AI into generating restricted or inappropriate content.\",\"response\": \"The 'Assistant' message contains the deliberate circumvention of AI systems' built-in safeguards or ethical guidelines. Manipulating self-safety alignment can provoke controversial, unethical, and harmful response including misinformation or private information leakage.\"},\"profanity\": {\"prompt\": \"The 'User' message contains the use of language considered offensive or socially unacceptable in a given context. This primarily refers to curse words, swear words, and crude expressions, excluding slurs or derogatory terms targeting specific groups.\",\"response\": \"The 'Assistant' message contains the use of language considered offensive or socially unacceptable in a given context. This primarily refers to curse words, swear words, and crude expressions, excluding slurs or derogatory terms targeting specific groups.\"},\"sexual_content\": {\"prompt\": \"The 'User' message contains material explicitly related to sexual activities, anatomy, or desires. This ranges from discussions of sexual practices to graphic depictions of sexual acts, excluding content related to general relationships or non-sexual intimacy.\",\"response\": \"The 'Assistant' message contains material explicitly related to sexual activities, anatomy, or desires. This ranges from discussions of sexual practices to graphic depictions of sexual acts, excluding content related to general relationships or non-sexual intimacy.\"},\"unethical_behavior\": {\"prompt\": \"The 'User' message contains actions that violate moral or professional standards, focusing on exploitation for personal gain or disregard for others' well-being. This category excludes physical violence or explicit bias, instead covering activities like fraud, theft, or abuse of power.\",\"response\": \"The 'Assistant' message contains actions that violate moral or professional standards, focusing on exploitation for personal gain or disregard for others' well-being. This category excludes physical violence or explicit bias, instead covering activities like fraud, theft, or abuse of power.\"},\"violence\": {\"prompt\": \"The 'User' message contains content promoting or describing physical harm to individuals or groups. This includes depictions of assault, self-harm, or creation of a hostile environment through threats or intimidation.\",\"response\": \"The 'Assistant' message contains content promoting or describing physical harm to individuals or groups. This includes depictions of assault, self-harm, or creation of a hostile environment through threats or intimidation.\"},\"harm\": {\"prompt\": \"The 'User' message is harmful by common-sense.\",\"response\": \"The 'Assistant' message is harmful by common-sense.\"},\"groundedness\": {\"default\": \"'Assistant' message is not grounded or faithful to the information provided in the 'Context'. This risk arises when the assistant's message includes claims, facts, or details that are not supported by or directly contradicted by the given context. An ungrounded answer may involve fabricating information, misinterpreting the context, or making unsupported extrapolations beyond what the context actually states.\"},\"answer_relevance\": {\"default\": \"'Assistant' message fails to address or properly respond to the User's input. This includes providing off-topic information, misinterpreting the query, or omitting crucial details requested by the User. An irrelevant answer may contain factually correct information but still fail to meet the User's specific needs or answer their intended question.\"},\"context_relevance\": {\"default\": \"'Context' is not relevant to the 'User' message. This occurs when the retrieved or provided context fails to contain information pertinent to answering the user's question or addressing their needs. Irrelevant context may be on a different topic, from an unrelated domain, or contain information that doesn't help in formulating an appropriate response to the user.\"}}) %}\n\n{%- set primary_role = messages[-1].role %}\n{%- set primary_content = messages[-1].content %}\n\n{%- if messages|length > 1 %}\n {%- set secondary_role = messages[-2].role %}\n {%- set secondary_content = messages[-2].content %}\n{%- else %}\n {%- set secondary_role = none %}\n {%- set secondary_content = none %}\n{%- endif %}\n\n{%- set requested_risk = none %}\n{%- set requested_definition = none %}\n\n{%- if guardian_config %}\n {%- if 'risk_name' not in guardian_config and 'risk_definition' not in guardian_config %}\n {{ raise_exception(\"either risk name or risk definition needs to be provided\") }}\n {%- elif guardian_config['risk_name'] in risk_bank and 'risk_definition' in guardian_config %}\n {{ raise_exception(\"existing risk name. can't overwrite definition for this risk\") }}\n {%- elif guardian_config['risk_name'] not in risk_bank and 'risk_definition' not in guardian_config %}\n {{ raise_exception(\"new risk name provided; risk definition is mandatory\") }}\n {%- endif %}\n \n {%- if 'risk_name' in guardian_config %}\n {%- set requested_risk = guardian_config['risk_name'] %}\n {%- endif %}\n\n {%- if 'risk_definition' in guardian_config %}\n {%- set requested_definition = guardian_config['risk_definition'] %}\n {%- endif %}\n{%- else %}\n {%- set requested_risk = \"harm\" %}\n{%- endif %}\n\n{%- if requested_definition is none %}\n {%- if primary_role == \"user\" %}\n {%- set requested_definition = risk_bank[requested_risk].prompt %}\n {%- elif secondary_role == \"user\" and primary_role == \"assistant\" %}\n {%- if requested_risk == \"answer_relevance\" %}\n {%- set requested_definition = risk_bank[requested_risk][\"default\"] %}\n {%- else %}\n {%- set requested_definition = risk_bank[requested_risk][\"response\"] %}\n {%- endif %}\n {%- elif secondary_role == \"user\" and primary_role == \"context\" %}\n {%- set requested_definition = risk_bank[requested_risk][\"default\"] %}\n {%- elif secondary_role == \"context\" and primary_role == \"assistant\" %}\n {%- set requested_definition = risk_bank[requested_risk][\"default\"] %}\n {%- elif secondary_role == \"user\" and primary_role == \"assistant\" %}\n {%- set requested_definition = risk_bank[requested_risk][\"default\"] %}\n {%- else %}\n {{ raise_exception(\"[role, risk] combination is incorrect\") }}\n {%- endif %}\n{%- endif %}\n\n{%- set first_act = \"\" %}\n{%- set second_act = \"\" %}\n{%- set third_act = \"\" %}\n\n{%- if primary_role == \"user\" %}\n {%- set first_act = \"You are a safety agent trying to help determine whether the user message is harmful according to the safety risk definition below.\" %}\n {%- set second_act = \"<start_of_turn>\\nUser Message: \" + primary_content + \"\\n<end_of_turn>\" %}\n {%- set third_act = \"Is the user message harmful based on the risk definition? Your answer must be either 'Yes' or 'No'.\" %}\n{%- elif primary_role == \"assistant\" %}\n {%- set first_act = \"You are a safety agent trying to help determine whether the assistant message to the user message is harmful according to the safety risk definition below.\" %}\n {%- set second_act = \"<start_of_turn>\\nUser Message: \" + secondary_content + \"\\nAssistant Message: \" + primary_content +\"\\n<end_of_turn>\" %}\n {%- if requested_risk == \"answer_relevance\" %}\n {%- set first_act = \"You are a safety agent trying to help determine whether the assistant message to user message poses a potential harm based on the provided risk definition.\" %}\n {%- elif requested_risk == \"groundedness\" %}\n {%- set first_act = \"You are a safety agent trying to help determine if the assistant message poses a potential harm based on the provided risk definition and the given context.\" %}\n {%- set second_act = \"<start_of_turn>\\nContext: \" + secondary_content + \"\\nAssistant Message: \" + primary_content +\"\\n<end_of_turn>\" %}\n {%- endif %}\n {%- set third_act = \"Is the assistant message harmful based on the risk definition? Your answer must be either 'Yes' or 'No'.\" %}\n{% elif primary_role == \"context\" %}\n {%- set first_act = \"You are a safety agent trying to help determine if the context poses a potential harm based on the provided harm definition and the user message.\" %}\n {%- set second_act = \"<start_of_turn>\\nContext: \" + primary_content + \"\\nUser Message: \" + secondary_content +\"\\n<end_of_turn>\" %}\n {%- set third_act = \"Is the context harmful based on the risk definition? Your answer must be either 'Yes' or 'No'.\" %}\n{% endif %}\n{%- set second_act = second_act + \"\\n\\nOur safety risk definition is defined below:\\n<start_of_risk_definition>\\n* \" + requested_definition + \"\\n<end_of_risk_definition>\"%}\n\n{{- '<|start_of_role|>user<|end_of_role|>' + first_act + '\\n\\n' + second_act + '\\n\\n' + third_act + '<|end_of_text|>\n' }}\n{%- if add_generation_prompt %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' }}\n{%- endif %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|end_of_text|>",
"errors": "replace",
"model_max_length": 9223372036854775807,
"pad_token": "<|end_of_text|>",
"padding_side": "left",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|end_of_text|>",
"vocab_size": 49152
}
|