chat_template.rs 56.7 KB
Newer Older
Nicolas Patry's avatar
Nicolas Patry committed
1
use crate::infer::InferError;
drbh's avatar
drbh committed
2
use crate::{ChatTemplateInputs, Message, MessageChunk, TextMessage, TokenizerConfigToken, Tool};
Nicolas Patry's avatar
Nicolas Patry committed
3
4
5
6
7
8
9
use minijinja::{Environment, ErrorKind, Template};
use minijinja_contrib::pycompat;

/// Raise a exception (custom function) used in the chat templates
pub(crate) fn raise_exception(err_text: String) -> Result<String, minijinja::Error> {
    Err(minijinja::Error::new(ErrorKind::SyntaxError, err_text))
}
10

Nicolas Patry's avatar
Nicolas Patry committed
11
12
13
14
15
16
#[derive(Clone)]
pub(crate) struct ChatTemplate {
    template: Template<'static, 'static>,
    bos_token: Option<String>,
    eos_token: Option<String>,
    use_default_tool_template: bool,
17
18
}

Nicolas Patry's avatar
Nicolas Patry committed
19
impl ChatTemplate {
20
    pub(crate) fn new(
Nicolas Patry's avatar
Nicolas Patry committed
21
22
23
        template: String,
        bos_token: Option<TokenizerConfigToken>,
        eos_token: Option<TokenizerConfigToken>,
24
    ) -> Self {
Nicolas Patry's avatar
Nicolas Patry committed
25
26
27
28
29
        let mut env = Box::new(Environment::new());
        // enable things like .strip() or .capitalize()
        env.set_unknown_method_callback(pycompat::unknown_method_callback);
        let template_str = template.into_boxed_str();
        env.add_function("raise_exception", raise_exception);
Nicolas Patry's avatar
Nicolas Patry committed
30
        tracing::debug!("Loading template: {}", template_str);
Nicolas Patry's avatar
Nicolas Patry committed
31
32
33
34
35

        // leaking env and template_str as read-only, static resources for performance.
        let template = Box::leak(env)
            .template_from_str(Box::leak(template_str))
            .unwrap();
36

37
38
39
40
        // get the list of variables that are used in the template
        let variables = template.undeclared_variables(true);
        // check if the `tools` variable is used in the template
        let use_default_tool_template = !variables.contains("tools");
drbh's avatar
drbh committed
41
        tracing::debug!("Use default tool template: {}", use_default_tool_template);
42

43
        Self {
Nicolas Patry's avatar
Nicolas Patry committed
44
45
46
47
            template,
            bos_token: bos_token.map(|token| token.as_str().to_string()),
            eos_token: eos_token.map(|token| token.as_str().to_string()),
            use_default_tool_template,
48
49
50
        }
    }

Nicolas Patry's avatar
Nicolas Patry committed
51
    pub(crate) fn apply(
52
        &self,
Nicolas Patry's avatar
Nicolas Patry committed
53
        mut messages: Vec<Message>,
drbh's avatar
drbh committed
54
        tools_and_prompt: Option<(Vec<Tool>, String)>,
Nicolas Patry's avatar
Nicolas Patry committed
55
    ) -> Result<String, InferError> {
drbh's avatar
drbh committed
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
        let tools = match tools_and_prompt {
            Some((tools, tool_prompt)) => {
                // check if the `tools` variable is used in the template
                // if not, we need to append the tools to the last message
                let text = if self.use_default_tool_template {
                    match serde_json::to_string(&tools) {
                        Ok(tools_str) => format!("\n---\n{}\n{}", tools_str, tool_prompt),
                        Err(e) => return Err(InferError::ToolError(e.to_string())),
                    }
                } else {
                    // if the `tools` variable is used in the template, we just append the tool_prompt
                    format!("\n---\n{}", tool_prompt)
                };
                if let Some(last_message) = messages.last_mut() {
                    last_message.content.push(MessageChunk::Text { text });
                }
                Some(tools)
            }
            None => None,
        };

        let messages: Vec<TextMessage> = messages.into_iter().map(|c| c.into()).collect();
drbh's avatar
drbh committed
78
79
80
        let final_message = messages.last().cloned();
        let mut rendered_template = self
            .template
Nicolas Patry's avatar
Nicolas Patry committed
81
82
83
84
85
            .render(ChatTemplateInputs {
                messages,
                bos_token: self.bos_token.as_deref(),
                eos_token: self.eos_token.as_deref(),
                add_generation_prompt: true,
drbh's avatar
drbh committed
86
                tools,
Nicolas Patry's avatar
Nicolas Patry committed
87
            })
drbh's avatar
drbh committed
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
            .map_err(InferError::TemplateError)?;

        // if the last message is from the assistant, continue the generation prompt
        rendered_template = match final_message {
            Some(msg) if msg.role == "assistant" => {
                match rendered_template.rfind(msg.content.as_str()) {
                    // implementation based on feature in transformers pipeline
                    // https://github.com/huggingface/transformers/blob/1cf17077bf2d4affed31387c0943251a4ba8fab7/src/transformers/pipelines/text_generation.py#L418
                    Some(index) => rendered_template[..index + msg.content.len()]
                        .trim_end()
                        .to_string(),
                    None => rendered_template,
                }
            }
            _ => rendered_template,
        };

        Ok(rendered_template)
106
107
    }
}
108
109
110
111

// tests
#[cfg(test)]
mod tests {
Nicolas Patry's avatar
Nicolas Patry committed
112
    use crate::infer::chat_template::raise_exception;
113
    use crate::infer::ChatTemplate;
drbh's avatar
drbh committed
114
    use crate::{
drbh's avatar
drbh committed
115
        ChatTemplateInputs, Message, MessageContent, TextMessage, TokenizerConfigToken, Tool,
drbh's avatar
drbh committed
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
    use minijinja::Environment;

    #[test]
    fn test_chat_template() {
        let env = Environment::new();

        let source = r#"
        {% for message in messages %}
            {% if message['role'] == 'system' %}
                {% if message['content']%}
                    {{'### System:\n' + message['content']+'\n\n'}}
                {% endif %}
            {% elif message['role'] == 'user' %}
                {{'### User:\n' + message['content']+'\n\n'}}
            {% elif message['role'] == 'assistant' %}
                {{'### Assistant:\n'  + message['content']}}
            {% endif %}
            {% if loop.last and add_generation_prompt %}
                {{ '### Assistant:\n' }}
            {% endif %}
        {% endfor %}"#;

        // trim all the whitespace
        let source = source
            .lines()
            .map(|line| line.trim())
            .collect::<Vec<&str>>()
            .join("");

        let tmpl = env.template_from_str(&source);

        let chat_template_inputs = ChatTemplateInputs {
            messages: vec![
Nicolas Patry's avatar
Nicolas Patry committed
150
                TextMessage {
151
                    role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
152
                    content: "Hi!".to_string(),
153
                },
Nicolas Patry's avatar
Nicolas Patry committed
154
                TextMessage {
155
                    role: "assistant".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
156
                    content: "Hello how can I help?".to_string(),
157
                },
Nicolas Patry's avatar
Nicolas Patry committed
158
                TextMessage {
159
                    role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
160
                    content: "What is Deep Learning?".to_string(),
161
                },
Nicolas Patry's avatar
Nicolas Patry committed
162
                TextMessage {
163
                    role: "assistant".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
164
                    content: "magic!".to_string(),
165
166
167
168
                },
            ],
            bos_token: Some("[BOS]"),
            eos_token: Some("[EOS]"),
169
            add_generation_prompt: true,
170
            ..Default::default()
171
172
173
174
175
176
        };

        let result = tmpl.unwrap().render(chat_template_inputs).unwrap();

        assert_eq!(
            result,
177
            "### User:\nHi!\n\n### Assistant:\nHello how can I help?### User:\nWhat is Deep Learning?\n\n### Assistant:\nmagic!### Assistant:\n"
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
        );
    }

    #[test]
    fn test_chat_template_invalid_with_raise() {
        let mut env = Environment::new();
        env.add_function("raise_exception", raise_exception);

        let source = r#"
        {{ bos_token }}
        {% for message in messages %}
        {% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
        {% endif %}
        {% if message['role'] == 'user' %}
        {{ '[INST] ' + message['content'] + ' [/INST]' }}
        {% elif message['role'] == 'assistant' %}
        {{ message['content'] + eos_token}}
        {% else %}
        {{ raise_exception('Only user and assistant roles are supported!') }}
        {% endif %}
        {% endfor %}"#;

        // trim all the whitespace
        let source = source
            .lines()
            .map(|line| line.trim())
            .collect::<Vec<&str>>()
            .join("");

        let tmpl = env.template_from_str(&source);

        let chat_template_inputs = ChatTemplateInputs {
            messages: vec![
Nicolas Patry's avatar
Nicolas Patry committed
212
                TextMessage {
213
                    role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
214
                    content: "Hi!".to_string(),
215
                },
Nicolas Patry's avatar
Nicolas Patry committed
216
                TextMessage {
217
                    role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
218
                    content: "Hi again!".to_string(),
219
                },
Nicolas Patry's avatar
Nicolas Patry committed
220
                TextMessage {
221
                    role: "assistant".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
222
                    content: "Hello how can I help?".to_string(),
223
                },
Nicolas Patry's avatar
Nicolas Patry committed
224
                TextMessage {
225
                    role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
226
                    content: "What is Deep Learning?".to_string(),
227
                },
Nicolas Patry's avatar
Nicolas Patry committed
228
                TextMessage {
229
                    role: "assistant".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
230
                    content: "magic!".to_string(),
231
232
233
234
                },
            ],
            bos_token: Some("[BOS]"),
            eos_token: Some("[EOS]"),
235
            add_generation_prompt: true,
236
            ..Default::default()
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
        };

        let result = tmpl.unwrap().render(chat_template_inputs); //.err().unwrap();

        match result {
            Ok(_) => panic!("Should have failed"),
            Err(e) => {
                assert_eq!(
                    e.detail().unwrap(),
                    "Conversation roles must alternate user/assistant/user/assistant/..."
                );
            }
        }
    }

    #[test]
    fn test_chat_template_valid_with_raise() {
        let mut env = Environment::new();
        env.add_function("raise_exception", raise_exception);

        let source = r#"
        {{ bos_token }}
        {% for message in messages %}
        {% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
        {% endif %}
        {% if message['role'] == 'user' %}
        {{ '[INST] ' + message['content'] + ' [/INST]' }}
        {% elif message['role'] == 'assistant' %}
        {{ message['content'] + eos_token}}
        {% else %}
        {{ raise_exception('Only user and assistant roles are supported!') }}
        {% endif %}
        {% endfor %}"#;

        // trim all the whitespace
        let source = source
            .lines()
            .map(|line| line.trim())
            .collect::<Vec<&str>>()
            .join("");

        let tmpl = env.template_from_str(&source);

        let chat_template_inputs = ChatTemplateInputs {
            messages: vec![
Nicolas Patry's avatar
Nicolas Patry committed
283
                TextMessage {
284
                    role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
285
                    content: "Hi!".to_string(),
286
                },
Nicolas Patry's avatar
Nicolas Patry committed
287
                TextMessage {
288
                    role: "assistant".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
289
                    content: "Hello how can I help?".to_string(),
290
                },
Nicolas Patry's avatar
Nicolas Patry committed
291
                TextMessage {
292
                    role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
293
                    content: "What is Deep Learning?".to_string(),
294
                },
Nicolas Patry's avatar
Nicolas Patry committed
295
                TextMessage {
296
                    role: "assistant".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
297
                    content: "magic!".to_string(),
298
299
300
301
                },
            ],
            bos_token: Some("[BOS]"),
            eos_token: Some("[EOS]"),
302
            add_generation_prompt: true,
303
            ..Default::default()
304
305
306
307
308
        };

        let result = tmpl.unwrap().render(chat_template_inputs).unwrap();
        assert_eq!(result, "[BOS][INST] Hi! [/INST]Hello how can I help?[EOS][INST] What is Deep Learning? [/INST]magic![EOS]");
    }
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333

    #[test]
    fn test_chat_template_valid_with_add_generation_prompt() {
        let mut env = Environment::new();
        env.add_function("raise_exception", raise_exception);

        let source = r#"
        {% for message in messages %}
        {{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}
        {% endfor %}
        {% if add_generation_prompt %}
            {{ '<|im_start|>assistant\n' }}
        {% endif %}"#;

        // trim all the whitespace
        let source = source
            .lines()
            .map(|line| line.trim())
            .collect::<Vec<&str>>()
            .join("");

        let tmpl = env.template_from_str(&source);

        let chat_template_inputs = ChatTemplateInputs {
            messages: vec![
Nicolas Patry's avatar
Nicolas Patry committed
334
                TextMessage {
335
                    role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
336
                    content: "Hi!".to_string(),
337
                },
Nicolas Patry's avatar
Nicolas Patry committed
338
                TextMessage {
339
                    role: "assistant".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
340
                    content: "Hello how can I help?".to_string(),
341
                },
Nicolas Patry's avatar
Nicolas Patry committed
342
                TextMessage {
343
                    role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
344
                    content: "What is Deep Learning?".to_string(),
345
                },
Nicolas Patry's avatar
Nicolas Patry committed
346
                TextMessage {
347
                    role: "assistant".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
348
                    content: "magic!".to_string(),
349
350
351
352
353
                },
            ],
            bos_token: Some("[BOS]"),
            eos_token: Some("[EOS]"),
            add_generation_prompt: true,
354
            ..Default::default()
355
356
357
358
359
        };

        let result = tmpl.unwrap().render(chat_template_inputs).unwrap();
        assert_eq!(result, "<|im_start|>user\nHi!<|im_end|>\n<|im_start|>assistant\nHello how can I help?<|im_end|>\n<|im_start|>user\nWhat is Deep Learning?<|im_end|>\n<|im_start|>assistant\nmagic!<|im_end|>\n<|im_start|>assistant\n");
    }
360
361
362
363
364
365
366
367
368
369
370

    struct ChatTemplateTestItem {
        name: &'static str,
        chat_template: &'static str,
        input: ChatTemplateInputs<'static>,
        target: &'static str,
    }

    #[test]
    fn test_many_chat_templates() {
        let example_chat = vec![
Nicolas Patry's avatar
Nicolas Patry committed
371
            TextMessage {
372
                role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
373
                content: "Hello, how are you?".to_string(),
374
            },
Nicolas Patry's avatar
Nicolas Patry committed
375
            TextMessage {
376
                role: "assistant".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
377
                content: "I'm doing great. How can I help you today?".to_string(),
378
            },
Nicolas Patry's avatar
Nicolas Patry committed
379
            TextMessage {
380
                role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
381
                content: "I'd like to show off how chat templating works!".to_string(),
382
383
384
            },
        ];

Nicolas Patry's avatar
Nicolas Patry committed
385
        let example_chat_with_system = [TextMessage {
386
            role: "system".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
387
388
            content: "You are a friendly chatbot who always responds in the style of a pirate"
                .to_string(),
389
390
391
392
393
394
395
396
397
398
        }]
        .iter()
        .chain(&example_chat)
        .cloned()
        .collect::<Vec<_>>();

        let test_default_templates = vec![
            ChatTemplateTestItem {
                name: "_base",
                chat_template: "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
399
                input: ChatTemplateInputs {
400
401
402
403
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some(""),
                    eos_token: Some(""),
404
                    ..Default::default()
405
406
407
408
409
410
                },
                target: "<|im_start|>user\nHello, how are you?<|im_end|>\n<|im_start|>assistant\nI'm doing great. How can I help you today?<|im_end|>\n<|im_start|>user\nI'd like to show off how chat templating works!<|im_end|>\n",
            },
            ChatTemplateTestItem {
                name: "blenderbot",
                chat_template: "{% for message in messages %}{% if message['role'] == 'user' %}{{ ' ' }}{% endif %}{{ message['content'] }}{% if not loop.last %}{{ '  ' }}{% endif %}{% endfor %}{{ eos_token }}",
411
                input: ChatTemplateInputs {
412
413
414
415
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some(""),
                    eos_token: Some("</s>"),
416
                    ..Default::default()
417
418
419
420
421
422
                },
                target: " Hello, how are you?  I'm doing great. How can I help you today?   I'd like to show off how chat templating works!</s>",
            },
            ChatTemplateTestItem {
                name: "blenderbot_small",
                chat_template: "{% for message in messages %}{% if message['role'] == 'user' %}{{ ' ' }}{% endif %}{{ message['content'] }}{% if not loop.last %}{{ '  ' }}{% endif %}{% endfor %}{{ eos_token }}",
423
                input: ChatTemplateInputs {
424
425
426
427
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some(""),
                    eos_token: Some("</s>"),
428
                    ..Default::default()
429
430
431
432
433
434
                },
                target: " Hello, how are you?  I'm doing great. How can I help you today?   I'd like to show off how chat templating works!</s>",
            },
            ChatTemplateTestItem {
                name: "bloom",
                chat_template: "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
435
                input: ChatTemplateInputs {
436
437
438
439
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some(""),
                    eos_token: Some("</s>"),
440
                    ..Default::default()
441
442
443
444
445
446
                },
                target: "Hello, how are you?</s>I'm doing great. How can I help you today?</s>I'd like to show off how chat templating works!</s>",
            },
            ChatTemplateTestItem {
                name: "gpt_neox",
                chat_template: "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
447
                input: ChatTemplateInputs {
448
449
450
451
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some(""),
                    eos_token: Some("<|endoftext|>"),
452
                    ..Default::default()
453
454
455
456
457
458
                },
                target: "Hello, how are you?<|endoftext|>I'm doing great. How can I help you today?<|endoftext|>I'd like to show off how chat templating works!<|endoftext|>",
            },
            ChatTemplateTestItem {
                name: "gpt2",
                chat_template: "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
459
460
461
462
463
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some(""),
                    eos_token: Some("<|endoftext|>"),
464
                    ..Default::default()
465
                },
466
                target: "Hello, how are you?<|endoftext|>I'm doing great. How can I help you today?<|endoftext|>I'd like to show off how chat templating works!<|endoftext|>",
467
468
469
470
471
            },
            ChatTemplateTestItem {
                name: "llama",
                // NOTE: the `.strip()` has been replaced with `| trim` in the following template
                chat_template: "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif USE_DEFAULT_PROMPT == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'DEFAULT_SYSTEM_MESSAGE' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token +'[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content | trim + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
472
473
474
475
476
                input: ChatTemplateInputs {
                    messages: example_chat_with_system.clone(),
                    add_generation_prompt: true,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
477
                    ..Default::default()
478
                },
479
                target: "<s>[INST] <<SYS>>\nYou are a friendly chatbot who always responds in the style of a pirate\n<</SYS>>\n\nHello, how are you? [/INST] I'm doing great. How can I help you today? </s><s>[INST] I'd like to show off how chat templating works! [/INST]",
480
481
482
483
            },
            ChatTemplateTestItem {
                name: "whisper",
                chat_template: "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
484
485
486
487
488
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: true,
                    bos_token: Some(""),
                    eos_token: Some("<|endoftext|>"),
489
                    ..Default::default()
490
                },
491
492
                target: "Hello, how are you?<|endoftext|>I'm doing great. How can I help you today?<|endoftext|>I'd like to show off how chat templating works!<|endoftext|>",
            },
493
494
495
496
497
498
499
500
501
502
503
504
        ];

        #[allow(unused_variables)] // name is unused
        for ChatTemplateTestItem {
            name,
            chat_template,
            input,
            target,
        } in test_default_templates
        {
            let mut env = Environment::new();
            env.add_function("raise_exception", raise_exception);
505
            let tmpl = env.template_from_str(chat_template);
506
507
508
509
510
511
512
513
514
515
516
517
            let result = tmpl.unwrap().render(input).unwrap();
            assert_eq!(result, target);
        }

        let test_custom_templates = vec![
            ChatTemplateTestItem {
                name: "HuggingFaceH4/zephyr-7b-beta (add_generation_prompt=false)",
                chat_template: "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
                input: ChatTemplateInputs {
                    messages: example_chat_with_system.clone(),
                    add_generation_prompt: false,
                    bos_token: Some(""),
518
                    eos_token: Some("</s>"),
519
                    ..Default::default()
520
521
522
523
524
525
526
527
                },
                target: "<|system|>\nYou are a friendly chatbot who always responds in the style of a pirate</s><|user|>\nHello, how are you?</s><|assistant|>\nI'm doing great. How can I help you today?</s><|user|>\nI'd like to show off how chat templating works!</s>",
            },
            ChatTemplateTestItem {
                name: "HuggingFaceH4/zephyr-7b-beta (add_generation_prompt=true)",
                chat_template: "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
                input: ChatTemplateInputs {
                    messages: vec![
OlivierDehaene's avatar
OlivierDehaene committed
528
                        TextMessage {
529
                            role: "system".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
530
                            content: "You are a friendly chatbot who always responds in the style of a pirate".to_string(),
531
                        },
OlivierDehaene's avatar
OlivierDehaene committed
532
                        TextMessage {
533
                            role: "user".to_string(),
Nicolas Patry's avatar
Nicolas Patry committed
534
                            content: "How many helicopters can a human eat in one sitting?".to_string(),
535
536
537
538
539
                        },
                    ],
                    add_generation_prompt: true,
                    bos_token: Some(""),
                    eos_token: Some("</s>"),
540
                    ..Default::default()
541
                },
542
                target: "<|system|>\nYou are a friendly chatbot who always responds in the style of a pirate</s><|user|>\nHow many helicopters can a human eat in one sitting?</s><|assistant|>",
543
544
545
546
547
548
549
550
551
            },
            ChatTemplateTestItem {
                name: "HuggingFaceH4/zephyr-7b-gemma-v0.1",
                chat_template: "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<bos>"),
                    eos_token: Some("<eos>"),
552
                    ..Default::default()
553
554
555
556
557
558
559
560
561
562
563
                },
                target: "<bos><|im_start|>user\nHello, how are you?<|im_end|>\n<|im_start|>assistant\nI'm doing great. How can I help you today?<|im_end|>\n<|im_start|>user\nI'd like to show off how chat templating works!<|im_end|>\n",
            },
            ChatTemplateTestItem {
                name: "mistralai/Mistral-7B-Instruct-v0.1",
                chat_template: "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
564
                    ..Default::default()
565
                },
566
                target: "<s>[INST] Hello, how are you? [/INST]I'm doing great. How can I help you today?</s> [INST] I'd like to show off how chat templating works! [/INST]",
567
568
569
570
571
572
573
574
575
            },
            ChatTemplateTestItem {
                name: "mistralai/Mixtral-8x7B-Instruct-v0.1",
                chat_template: "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
576
                    ..Default::default()
577
578
579
580
581
582
583
                },
                target: "<s>[INST] Hello, how are you? [/INST]I'm doing great. How can I help you today?</s>[INST] I'd like to show off how chat templating works! [/INST]",
            },
            ChatTemplateTestItem {
                name: "cognitivecomputations/dolphin-2.5-mixtral-8x7b",
                chat_template: "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
                input: ChatTemplateInputs {
584
                    messages: example_chat.clone(),
585
586
587
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
588
                    ..Default::default()
589
590
591
592
593
594
595
596
597
598
599
600
                },
                target: "<|im_start|>user\nHello, how are you?<|im_end|>\n<|im_start|>assistant\nI'm doing great. How can I help you today?<|im_end|>\n<|im_start|>user\nI'd like to show off how chat templating works!<|im_end|>\n",
            },
            ChatTemplateTestItem {
                name: "openchat/openchat-3.5-0106",
                // `.title()` has been replaced with `| upper` in the following template
                chat_template: "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + (message['role'] | title) + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
601
                    ..Default::default()
602
603
604
605
606
607
608
609
610
611
612
                },
                target: "<s>GPT4 Correct User: Hello, how are you?<|end_of_turn|>GPT4 Correct Assistant: I'm doing great. How can I help you today?<|end_of_turn|>GPT4 Correct User: I'd like to show off how chat templating works!<|end_of_turn|>",
            },
            ChatTemplateTestItem {
                name: "upstage/SOLAR-10.7B-Instruct-v1.0",
                chat_template: "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
613
                    ..Default::default()
614
615
616
617
618
619
620
621
622
623
624
625
                },
                target: "Hello, how are you?</s>I'm doing great. How can I help you today?</s>I'd like to show off how chat templating works!</s>",
            },
            ChatTemplateTestItem {
                name: "codellama/CodeLlama-70b-Instruct-hf",
                // NOTE: `.strip()` has been replaced with `| trim` in the following template
                chat_template: "{% if messages[0]['role'] == 'system' %}{% set user_index = 1 %}{% else %}{% set user_index = 0 %}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != ((loop.index0 + user_index) % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 %}{{ '<s>' }}{% endif %}{% set content = 'Source: ' + message['role'] + '\\n\\n ' + message['content'] | trim %}{{ content + ' <step> ' }}{% endfor %}{{'Source: assistant\\nDestination: user\\n\\n '}}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
626
                    ..Default::default()
627
628
629
630
631
632
633
634
635
636
637
                },
                target: "<s>Source: user\n\n Hello, how are you? <step> Source: assistant\n\n I'm doing great. How can I help you today? <step> Source: user\n\n I'd like to show off how chat templating works! <step> Source: assistant\nDestination: user\n\n ",
            },
            ChatTemplateTestItem {
                name: "Deci/DeciLM-7B-instruct",
                chat_template: "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### User:\\n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ '### System:\\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '### Assistant:\\n'  + message['content'] }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Assistant:' }}\n{% endif %}\n{% endfor %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
638
                    ..Default::default()
639
640
641
642
643
644
645
646
647
648
649
                },
                target: "### User:\nHello, how are you?### Assistant:\nI'm doing great. How can I help you today?### User:\nI'd like to show off how chat templating works!",
            },
            ChatTemplateTestItem {
                name: "Qwen/Qwen1.5-72B-Chat",
                chat_template: "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\\nYou are a helpful assistant<|im_end|>\\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
650
                    ..Default::default()
651
652
653
654
655
656
657
658
659
660
661
                },
                target: "<|im_start|>system\nYou are a helpful assistant<|im_end|>\n<|im_start|>user\nHello, how are you?<|im_end|>\n<|im_start|>assistant\nI'm doing great. How can I help you today?<|im_end|>\n<|im_start|>user\nI'd like to show off how chat templating works!",
            },
            ChatTemplateTestItem {
                name: "deepseek-ai/deepseek-llm-7b-chat",
                chat_template: "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\\n\\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<|begin▁of▁sentence|>"),
                    eos_token: Some("<|end▁of▁sentence|>"),
662
                    ..Default::default()
663
664
665
666
667
668
669
670
671
672
673
                },
                target: "<|begin▁of▁sentence|>User: Hello, how are you?\n\nAssistant: I'm doing great. How can I help you today?<|end▁of▁sentence|>User: I'd like to show off how chat templating works!\n\n",
            },
            ChatTemplateTestItem {
                name: "h2oai/h2o-danube-1.8b-chat",
                chat_template: "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|prompt|>' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ '<|system|>' + message['content'] + eos_token }}{% elif message['role'] == 'assistant' %}{{ '<|answer|>'  + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|answer|>' }}{% endif %}{% endfor %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
674
                    ..Default::default()
675
                },
676
                target: "<|prompt|>Hello, how are you?</s><|answer|>I'm doing great. How can I help you today?</s><|prompt|>I'd like to show off how chat templating works!</s>",
677
678
679
680
681
682
683
684
685
            },
            ChatTemplateTestItem {
                name: "internlm/internlm2-chat-7b",
                chat_template: "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
686
                    ..Default::default()
687
688
689
690
691
692
693
694
695
696
697
                },
                target: "<s><|im_start|>user\nHello, how are you?<|im_end|>\n<|im_start|>assistant\nI'm doing great. How can I help you today?<|im_end|>\n<|im_start|>user\nI'd like to show off how chat templating works!<|im_end|>\n",
            },
            ChatTemplateTestItem {
                name: "TheBloke/deepseek-coder-33B-instruct-AWQ",
                chat_template: "{%- set found_item = false -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set found_item = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{%- if not found_item -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{{'### Response:\\n'}}\n",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<|begin▁of▁sentence|>"),
                    eos_token: Some("<|EOT|>"),
698
                    ..Default::default()
699
700
701
702
703
704
705
706
707
708
709
710
                },
                target: "You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.\n### Instruction:\nHello, how are you?\n### Response:\nI'm doing great. How can I help you today?\n<|EOT|>\n### Instruction:\nI'd like to show off how chat templating works!\n### Response:\n",
            },
            ChatTemplateTestItem {
                name: "ericzzz/falcon-rw-1b-chat",
                // `.strip()` has been replaced with `| trim` in the following template
                chat_template: "{% for message in messages %}{% if loop.index > 1 and loop.previtem['role'] != 'assistant' %}{{ ' ' }}{% endif %}{% if message['role'] == 'system' %}{{ '[SYS] ' + message['content'] | trim }}{% elif message['role'] == 'user' %}{{ '[INST] ' + message['content'] | trim }}{% elif message['role'] == 'assistant' %}{{ '[RESP] '  + message['content'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ ' [RESP] ' }}{% endif %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<|endoftext|>"),
                    eos_token: Some("<|endoftext|>"),
711
                    ..Default::default()
712
713
714
715
716
717
718
719
720
721
722
                },
                target: "[INST] Hello, how are you? [RESP] I'm doing great. How can I help you today?<|endoftext|>[INST] I'd like to show off how chat templating works!",
            },
            ChatTemplateTestItem {
                name: "abacusai/Smaug-34B-v0.1",
                chat_template: "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' '  + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
723
                    ..Default::default()
724
725
726
727
728
729
730
731
732
733
734
                },
                target: "Hello, how are you? [/INST] I'm doing great. How can I help you today? </s><s>[INST] I'd like to show off how chat templating works! [/INST]",
            },
            ChatTemplateTestItem {
                name: "maywell/Synatra-Mixtral-8x7B",
                chat_template: "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n{% for message in messages %}{% if message['role'] == 'user' %}### Instruction:\n{{ message['content']|trim -}}{% if not loop.last %}{% endif %}\n{% elif message['role'] == 'assistant' %}### Response:\n{{ message['content']|trim -}}{% if not loop.last %}{% endif %}\n{% elif message['role'] == 'system' %}{{ message['content']|trim -}}{% if not loop.last %}{% endif %}\n{% endif %}\n{% endfor %}\n{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}\n### Response:\n{% endif %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
735
                    ..Default::default()
736
737
738
739
740
741
742
743
744
745
746
                },
                target: "Below is an instruction that describes a task. Write a response that appropriately completes the request.### 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: "deepseek-ai/deepseek-coder-33b-instruct",
                chat_template: "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
                input: ChatTemplateInputs {
                    messages: example_chat.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<|begin▁of▁sentence|>"),
                    eos_token: Some("</EOT>"),
747
                    ..Default::default()
748
749
750
751
                },
                target: "<|begin▁of▁sentence|>You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\n### Instruction:\nHello, how are you?\n### Response:\nI'm doing great. How can I help you today?\n<|EOT|>\n### Instruction:\nI'd like to show off how chat templating works!\n",
            },
            // NOT INCLUDED
OlivierDehaene's avatar
OlivierDehaene committed
752
            // - meetkai/functionary-medium-v3.2
753
754
755
756
757
758
759
760
761
762
            // - fireworks-ai/firefunction-v1
            // https://github
            ChatTemplateTestItem {
                name: "maywell/PiVoT-MoE",
                chat_template: "{{ (messages|selectattr('role', 'equalto', 'system')|list|last).content|trim if (messages|selectattr('role', 'equalto', 'system')|list) else '' }}{% for message in messages %}{% if message['role'] == 'system' %}{{ message['content']|trim }}{% elif message['role'] == 'user' %}### Instruction: {{ message['content']|trim }}{% elif message['role'] == 'assistant' %}### Response: {{ message['content']|trim }}{% elif message['role'] == 'user_context' %}### Input: {{ message['content']|trim }}{% endif %}{% if not loop.last %}\n{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}### Response:{% endif %}",
                input: ChatTemplateInputs {
                    messages: example_chat_with_system.clone(),
                    add_generation_prompt: false,
                    bos_token: Some("<s>"),
                    eos_token: Some("</s>"),
763
                    ..Default::default()
764
765
                },
                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!",
766
            },
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
        ];

        #[allow(unused_variables)] // name is unused
        for ChatTemplateTestItem {
            name,
            chat_template,
            input,
            target,
        } in test_custom_templates
        {
            let mut env = Environment::new();
            env.add_function("raise_exception", raise_exception);
            // trim all the whitespace
            let chat_template = chat_template
                .lines()
                .map(|line| line.trim())
                .collect::<Vec<&str>>()
                .join("");

            let tmpl = env.template_from_str(&chat_template);
            let result = tmpl.unwrap().render(input).unwrap();
            assert_eq!(result, target);
        }
    }
791

drbh's avatar
drbh committed
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
    #[test]
    fn test_chat_template_with_default_tool_template() {
        let ct = ChatTemplate::new(
            "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}".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("Great! How can I help you today?".to_string()),
            },
            Message {
                name: None,
                role: "user".to_string(),
                content: MessageContent::SingleText("Just testing".to_string()),
            },
        ];
drbh's avatar
drbh committed
820
821
        let tools_string = r#"[{"type": "function","function": {"name": "get_current_weather","description": "Get the current weather","parameters": {"type": "object","properties": {"location": {"type": "string","description": "The city and state, e.g. San Francisco, CA"},"format": {"type": "string","enum": ["celsius", "fahrenheit"],"description": "The temperature unit to use. Infer this from the users location."}},"required": ["location", "format"]}}}]"#.to_string();
        let tools: Vec<Tool> = serde_json::from_str(&tools_string).unwrap();
drbh's avatar
drbh committed
822
        let tool_prompt = "This default prompt will be used".to_string();
drbh's avatar
drbh committed
823
        let tools_and_prompt = Some((tools, tool_prompt));
824
        let result = ct.apply(msgs, tools_and_prompt);
825
        let expected = "<s>[INST] I'd like to show off how chat templating works! [/INST]Great! How can I help you today?</s> [INST] Just testing\n---\n[{\"type\":\"function\",\"function\":{\"description\":\"Get the current weather\",\"name\":\"get_current_weather\",\"arguments\":{\"type\":\"object\",\"properties\":{\"location\":{\"type\":\"string\",\"description\":\"The city and state, e.g. San Francisco, CA\"},\"format\":{\"type\":\"string\",\"enum\":[\"celsius\",\"fahrenheit\"],\"description\":\"The temperature unit to use. Infer this from the users location.\"}},\"required\":[\"location\",\"format\"]}}}]\nThis default prompt will be used [/INST]".to_string();
drbh's avatar
drbh committed
826
827
        assert_eq!(result.unwrap(), expected);
    }
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857

    #[test]
    fn test_chat_template_with_custom_tool_template() {
        // chat template from meta-llama/Meta-Llama-3.1-8B-Instruct
        let ct = ChatTemplate::new(
            "{{- bos_token }}\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".to_string(),
            Some(TokenizerConfigToken::String("<s>".to_string())),
            Some(TokenizerConfigToken::String("</s>".to_string())),
        );
        let msgs: Vec<Message> = vec![
            Message {
                name: None,
                role: "system".to_string(),
                content: MessageContent::SingleText(
                    "Youre a helpful assistant! Answer the users question best you can."
                        .to_string(),
                ),
            },
            Message {
                name: None,
                role: "user".to_string(),
                content: MessageContent::SingleText(
                    "What is the weather like in Brooklyn, New York?".to_string(),
                ),
            },
        ];
        let tools_string = r#"[{"type": "function","function": {"name": "get_current_weather","description": "Get the current weather","parameters": {"type": "object","properties": {"location": {"type": "string","description": "The city and state, e.g. San Francisco, CA"},"format": {"type": "string","enum": ["celsius", "fahrenheit"],"description": "The temperature unit to use. Infer this from the users location."}},"required": ["location", "format"]}}}]"#.to_string();
        let tools: Vec<Tool> = serde_json::from_str(&tools_string).unwrap();
        let tool_prompt = "This default prompt will be used".to_string();
        let tools_and_prompt = Some((tools, tool_prompt));
858
        let result = ct.apply(msgs, tools_and_prompt);
859
860
861
        let expected = "<s><|start_header_id|>system<|end_header_id|>\n\nEnvironment: ipython\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\nYoure a helpful assistant! Answer the users question best you can.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nGiven the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.\n\nRespond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.Do not use variables.\n\n{\n    \"function\": {\n        \"arguments\": {\n            \"properties\": {\n                \"format\": {\n                    \"description\": \"The temperature unit to use. Infer this from the users location.\",\n                    \"enum\": [\n                        \"celsius\",\n                        \"fahrenheit\"\n                    ],\n                    \"type\": \"string\"\n                },\n                \"location\": {\n                    \"description\": \"The city and state, e.g. San Francisco, CA\",\n                    \"type\": \"string\"\n                }\n            },\n            \"required\": [\n                \"location\",\n                \"format\"\n            ],\n            \"type\": \"object\"\n        },\n        \"description\": \"Get the current weather\",\n        \"name\": \"get_current_weather\"\n    },\n    \"type\": \"function\"\n}\n\nWhat is the weather like in Brooklyn, New York?\n---\nThis default prompt will be used<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n".to_string();
        assert_eq!(result.unwrap(), expected);
    }
862
}