201 lines
18 KiB
JSON
201 lines
18 KiB
JSON
|
{
|
||
|
|
"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": [
|
||
|
|
"None",
|
||
|
|
"<|start_of_role|>",
|
||
|
|
"<|end_of_role|>",
|
||
|
|
"<|tool_call|>"
|
||
|
|
],
|
||
|
|
"bos_token": "<|end_of_text|>",
|
||
|
|
"chat_template": "{%- set risk_types_rag = [ \"groundedness\", \"answer_relevance\", \"context_relevance\", \"function_call\"] -%}\n{%- set risk_types_conv = [\"evasiveness\", \"harm_engagement\"] -%}\n\n{%- set risk_types = ({\n \"harm\": {\n \"user\": \"The last 'User' message is considered universally harmful.\",\n \"assistant\": \"The last 'Assistant' is message considered universally harmful.\"\n },\n \"social_bias\": {\n \"user\": \"The last '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.\",\n \"assistant\": \"The last '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.\"\n },\n \"jailbreak\": {\n \"user\": \"The last '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.\",\n \"assistant\": \"The last '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.\"\n },\n \"profanity\": {\n \"user\": \"The last '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.\",\n \"assistant\": \"The last '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.\"\n },\n \"sexual_content\": {\n \"user\": \"The last '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.\",\n \"assistant\": \"The last '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.\"\n },\n \"unethical_behavior\": {\n \"user\": \"The last '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.\",\n \"assistant\": \"The last '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.\"\n },\n \"violence\": {\n \"user\": \"The last '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.\",\n \"assistant\": \"The last '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 th
|
||
|
|
"clean_up_tokenization_spaces": true,
|
||
|
|
"eos_token": "<|end_of_text|>",
|
||
|
|
"errors": "replace",
|
||
|
|
"extra_special_tokens": {},
|
||
|
|
"model_max_length": 8192,
|
||
|
|
"pad_token": "<|end_of_text|>",
|
||
|
|
"padding_side": "left",
|
||
|
|
"tokenizer_class": "GPT2Tokenizer",
|
||
|
|
"unk_token": "<|end_of_text|>",
|
||
|
|
"vocab_size": 49152
|
||
|
|
}
|