Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: remove guideline tests

This commit is contained in:
drbh 2024-11-22 14:12:18 -05:00
parent 8770b39c20
commit 13a75acd76
1 changed files with 0 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
router/src/infer/chat_template.rs
View File

@ -764,18 +764,6 @@ mod tests {
},
target: "You are a friendly chatbot who always responds in the style of a pirateYou are a friendly chatbot who always responds in the style of a pirate### Instruction: Hello, how are you?### Response: I'm doing great. How can I help you today?### Instruction: I'd like to show off how chat templating works!",
},
ChatTemplateTestItem {
name: "google/shieldgemma-9b",
chat_template: "{{- bos_token }}\n{%- if messages[-1].role == 'user' %}\n {{- \"You are a policy expert trying to help determine whether a user prompt is in violation of the defined safety policies.\\n\\n\" }}\n {{- \"<start_of_turn>\\n\" }}\n {{- \"Human Question: \" + messages[-1].content }}\n {{- \"\\n<end_of_turn>\\n\\n\" }}\n {{- \"Our safety principle is defined in the below:\\n\\n\" }}\n {{- \"* \" + guideline + \"\\n\" }}\n {{- \"\\n===\\n\\n\" }}\n {{- \"Does the human question violate the above principle? Your answer must start with 'Yes' or 'No'. And then walk through step by step to be sure we answer correctly.\\n\\n\" }}\n{%- else %}\n {{- \"You are a policy expert trying to help determine whether an AI response to a prompt is in violation of the defined safety policies.\\n\\n\" }}\n {{- \"<start_of_turn>\\n\" }}\n {{- \"Human Question: \" + messages[-2].content }}\n {{- \"\\n<end_of_turn>\\n\" }}\n {{- \"<start_of_turn>\\n\" }}\n {{- \"Chatbot Response: \" + messages[-1].content }}\n {{- \"\\n<end_of_turn>\\n\\n\" }}\n {{- \"Our safety principle is defined in the below:\\n\\n\" }}\n {{- \"* \" + guideline + \"\\n\" }}\n {{- \"\\n===\\n\\n\" }}\n {{- \"Does the Chatbot Response violate the above principle? Your answer must start with 'Yes' or 'No'. And then walk through step by step to be sure we answer correctly.\\n\\n\" }}\n{%- endif %}\n\n",
input: ChatTemplateInputs {
messages: example_chat_with_system.clone(),
add_generation_prompt: false,
bos_token: Some("<s>"),
eos_token: Some("</s>"),
..Default::default()
},
target: "<s>You are a policy expert trying to help determine whether a user prompt is in violation of the defined safety policies.\n\n<start_of_turn>\nHuman Question: I'd like to show off how chat templating works!\n<end_of_turn>\n\nOur safety principle is defined in the below:\n\n* Do not use offensive language.\n\n===\n\nDoes the human question violate the above principle? Your answer must start with 'Yes' or 'No'. And then walk through step by step to be sure we answer correctly.\n\n",
},
];
#[allow(unused_variables)] // name is unused
@ -801,47 +789,6 @@ mod tests {
}
}
#[test]
fn test_chat_template_invalid_with_guideline() {
let ct = ChatTemplate::new(
"{{- bos_token }}\n{%- if messages[-1].role == 'user' %}\n {{- \"You are a policy expert trying to help determine whether a user prompt is in violation of the defined safety policies.\\n\\n\" }}\n {{- \"<start_of_turn>\\n\" }}\n {{- \"Human Question: \" + messages[-1].content }}\n {{- \"\\n<end_of_turn>\\n\\n\" }}\n {{- \"Our safety principle is defined in the below:\\n\\n\" }}\n {{- \"* \" + guideline + \"\\n\" }}\n {{- \"\\n===\\n\\n\" }}\n {{- \"Does the human question violate the above principle? Your answer must start with 'Yes' or 'No'. And then walk through step by step to be sure we answer correctly.\\n\\n\" }}\n{%- else %}\n {{- \"You are a policy expert trying to help determine whether an AI response to a prompt is in violation of the defined safety policies.\\n\\n\" }}\n {{- \"<start_of_turn>\\n\" }}\n {{- \"Human Question: \" + messages[-2].content }}\n {{- \"\\n<end_of_turn>\\n\" }}\n {{- \"<start_of_turn>\\n\" }}\n {{- \"Chatbot Response: \" + messages[-1].content }}\n {{- \"\\n<end_of_turn>\\n\\n\" }}\n {{- \"Our safety principle is defined in the below:\\n\\n\" }}\n {{- \"* \" + guideline + \"\\n\" }}\n {{- \"\\n===\\n\\n\" }}\n {{- \"Does the Chatbot Response violate the above principle? Your answer must start with 'Yes' or 'No'. And then walk through step by step to be sure we answer correctly.\\n\\n\" }}\n{%- endif %}\n\n".to_string(),
Some(TokenizerConfigToken::String("<s>".to_string())),
Some(TokenizerConfigToken::String("</s>".to_string())),
);
// convert TextMessage to Message
let msgs: Vec<Message> = vec![
Message {
name: None,
role: "user".to_string(),
content: MessageContent::SingleText(
"I'd like to show off how chat templating works!".to_string(),
),
},
Message {
name: None,
role: "assistant".to_string(),
content: MessageContent::SingleText(
"I'm doing great. How can I help you today?".to_string(),
),
},
Message {
name: None,
role: "user".to_string(),
content: MessageContent::SingleText("Hello, how are you?".to_string()),
},
];
let result = ct.apply(msgs, None);
match result {
Ok(_) => panic!("Should have failed since no guideline is provided"),
Err(e) => {
assert_eq!(e.to_string(), "Missing template vatiable: guideline")
}
}
}
#[test]
fn test_chat_template_with_default_tool_template() {
let ct = ChatTemplate::new(