aboutsummaryrefslogtreecommitdiff
path: root/examples/main/main.cpp
blob: 2248c245875b04b88ed84c17e0a6b50ba9825134 (plain)
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
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
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
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
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
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
// Defines sigaction on msys:
#ifndef _GNU_SOURCE
#define _GNU_SOURCE
#endif

#include "common.h"
#include "llama.h"
#include "build-info.h"

#include <cassert>
#include <cinttypes>
#include <cmath>
#include <cstdio>
#include <cstring>
#include <ctime>
#include <fstream>
#include <iostream>
#include <string>
#include <vector>

#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__))
#include <signal.h>
#include <unistd.h>
#elif defined (_WIN32)
#define WIN32_LEAN_AND_MEAN
#ifndef NOMINMAX
#define NOMINMAX
#endif
#include <windows.h>
#include <signal.h>
#endif

#if defined(_MSC_VER)
#pragma warning(disable: 4244 4267) // possible loss of data
#endif

static console_state con_st;
static llama_context ** g_ctx;

static bool is_interacting = false;

#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__)) || defined (_WIN32)
void sigint_handler(int signo) {
    if (signo == SIGINT) {
        if (!is_interacting) {
            is_interacting=true;
        } else {
            console_cleanup(con_st);
            printf("\n");
            llama_print_timings(*g_ctx);
            _exit(130);
        }
    }
}
#endif

int main(int argc, char ** argv) {
    gpt_params params;

    if (gpt_params_parse(argc, argv, params) == false) {
        return 1;
    }

    // save choice to use color for later
    // (note for later: this is a slightly awkward choice)
    con_st.use_color = params.use_color;
    con_st.multiline_input = params.multiline_input;
    console_init(con_st);
    atexit([]() { console_cleanup(con_st); });

    if (params.perplexity) {
        printf("\n************\n");
        printf("%s: please use the 'perplexity' tool for perplexity calculations\n", __func__);
        printf("************\n\n");

        return 0;
    }

    if (params.embedding) {
        printf("\n************\n");
        printf("%s: please use the 'embedding' tool for embedding calculations\n", __func__);
        printf("************\n\n");

        return 0;
    }

    if (params.n_ctx > 2048) {
        fprintf(stderr, "%s: warning: model might not support context sizes greater than 2048 tokens (%d specified);"
                "expect poor results\n", __func__, params.n_ctx);
    } else if (params.n_ctx < 8) {
        fprintf(stderr, "%s: warning: minimum context size is 8, using minimum size.\n", __func__);
        params.n_ctx = 8;
    }

    fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);

    if (params.seed == LLAMA_DEFAULT_SEED) {
        params.seed = time(NULL);
    }

    fprintf(stderr, "%s: seed  = %u\n", __func__, params.seed);

    std::mt19937 rng(params.seed);
    if (params.random_prompt) {
        params.prompt = gpt_random_prompt(rng);
    }

    llama_backend_init(params.numa);

    llama_model * model;
    llama_context * ctx;
    llama_context * ctx_guidance = NULL;
    g_ctx = &ctx;

    // load the model and apply lora adapter, if any
    std::tie(model, ctx) = llama_init_from_gpt_params(params);
    if (params.cfg_scale > 1.f) {
        struct llama_context_params lparams = llama_context_params_from_gpt_params(params);
        ctx_guidance = llama_new_context_with_model(model, lparams);
    }

    if (model == NULL) {
        fprintf(stderr, "%s: error: unable to load model\n", __func__);
        return 1;
    }

    // print system information
    {
        fprintf(stderr, "\n");
        fprintf(stderr, "system_info: n_threads = %d / %d | %s\n",
                params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info());
    }

    // determine the maximum memory usage needed to do inference for the given n_batch and n_predict parameters
    // uncomment the "used_mem" line in llama.cpp to see the results
    if (params.mem_test) {
        {
            const std::vector<llama_token> tmp(params.n_batch, llama_token_bos());
            llama_eval(ctx, tmp.data(), tmp.size(), 0, params.n_threads);
        }

        {
            const std::vector<llama_token> tmp = { 0, };
            llama_eval(ctx, tmp.data(), tmp.size(), params.n_predict - 1, params.n_threads);
        }

        llama_print_timings(ctx);
        llama_free(ctx);
        llama_free_model(model);

        return 0;
    }

    // export the cgraph and exit
    if (params.export_cgraph) {
        llama_eval_export(ctx, "llama.ggml");
        llama_free(ctx);
        llama_free_model(model);

        return 0;
    }

    std::string path_session = params.path_prompt_cache;
    std::vector<llama_token> session_tokens;

    if (!path_session.empty()) {
        fprintf(stderr, "%s: attempting to load saved session from '%s'\n", __func__, path_session.c_str());

        // fopen to check for existing session
        FILE * fp = std::fopen(path_session.c_str(), "rb");
        if (fp != NULL) {
            std::fclose(fp);

            session_tokens.resize(params.n_ctx);
            size_t n_token_count_out = 0;
            if (!llama_load_session_file(ctx, path_session.c_str(), session_tokens.data(), session_tokens.capacity(), &n_token_count_out)) {
                fprintf(stderr, "%s: error: failed to load session file '%s'\n", __func__, path_session.c_str());
                return 1;
            }
            session_tokens.resize(n_token_count_out);
            llama_set_rng_seed(ctx, params.seed);

            fprintf(stderr, "%s: loaded a session with prompt size of %d tokens\n", __func__, (int) session_tokens.size());
        } else {
            fprintf(stderr, "%s: session file does not exist, will create\n", __func__);
        }
    }

    // tokenize the prompt
    std::vector<llama_token> embd_inp;

    // Add a space in front of the first character to match OG llama tokenizer behavior
    params.prompt.insert(0, 1, ' ');

    if (params.interactive_first || params.instruct || !params.prompt.empty() || session_tokens.empty()) {
        embd_inp = ::llama_tokenize(ctx, params.prompt, true);
    } else {
        embd_inp = session_tokens;
    }

    // Tokenize negative prompt
    std::vector<llama_token> guidance_inp;
    int guidance_offset = 0;
    int original_prompt_len = 0;
    if (ctx_guidance) {
        params.cfg_negative_prompt.insert(0, 1, ' ');
        guidance_inp = ::llama_tokenize(ctx_guidance, params.cfg_negative_prompt, true);

        std::vector<llama_token> original_inp = ::llama_tokenize(ctx, params.prompt, true);
        original_prompt_len = original_inp.size();
        guidance_offset = (int)guidance_inp.size() - original_prompt_len;
    }

    const int n_ctx = llama_n_ctx(ctx);

    if ((int) embd_inp.size() > n_ctx - 4) {
        fprintf(stderr, "%s: error: prompt is too long (%d tokens, max %d)\n", __func__, (int) embd_inp.size(), n_ctx - 4);
        return 1;
    }

    // debug message about similarity of saved session, if applicable
    size_t n_matching_session_tokens = 0;
    if (session_tokens.size()) {
        for (llama_token id : session_tokens) {
            if (n_matching_session_tokens >= embd_inp.size() || id != embd_inp[n_matching_session_tokens]) {
                break;
            }
            n_matching_session_tokens++;
        }
        if (params.prompt.empty() && n_matching_session_tokens == embd_inp.size()) {
            fprintf(stderr, "%s: using full prompt from session file\n", __func__);
        } else if (n_matching_session_tokens >= embd_inp.size()) {
            fprintf(stderr, "%s: session file has exact match for prompt!\n", __func__);
        } else if (n_matching_session_tokens < (embd_inp.size() / 2)) {
            fprintf(stderr, "%s: warning: session file has low similarity to prompt (%zu / %zu tokens); will mostly be reevaluated\n",
                __func__, n_matching_session_tokens, embd_inp.size());
        } else {
            fprintf(stderr, "%s: session file matches %zu / %zu tokens of prompt\n",
                __func__, n_matching_session_tokens, embd_inp.size());
        }
    }

    // if we will use the cache for the full prompt without reaching the end of the cache, force
    // reevaluation of the last token token to recalculate the cached logits
    if (!embd_inp.empty() && n_matching_session_tokens == embd_inp.size() &&
            session_tokens.size() > embd_inp.size()) {
        session_tokens.resize(embd_inp.size() - 1);
    }

    // number of tokens to keep when resetting context
    if (params.n_keep < 0 || params.n_keep > (int) embd_inp.size() || params.instruct) {
        params.n_keep = (int)embd_inp.size();
    }

    // prefix & suffix for instruct mode
    const auto inp_pfx = ::llama_tokenize(ctx, "\n\n### Instruction:\n\n", true);
    const auto inp_sfx = ::llama_tokenize(ctx, "\n\n### Response:\n\n", false);

    // in instruct mode, we inject a prefix and a suffix to each input by the user
    if (params.instruct) {
        params.interactive_first = true;
        params.antiprompt.push_back("### Instruction:\n\n");
    }

    // enable interactive mode if interactive start is specified
    if (params.interactive_first) {
        params.interactive = true;
    }

    // determine newline token
    auto llama_token_newline = ::llama_tokenize(ctx, "\n", false);

    if (params.verbose_prompt) {
        fprintf(stderr, "\n");
        fprintf(stderr, "%s: prompt: '%s'\n", __func__, params.prompt.c_str());
        fprintf(stderr, "%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size());
        for (int i = 0; i < (int) embd_inp.size(); i++) {
            fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_str(ctx, embd_inp[i]));
        }

        if (ctx_guidance) {
            fprintf(stderr, "\n");
            fprintf(stderr, "%s: negative prompt: '%s'\n", __func__, params.cfg_negative_prompt.c_str());
            fprintf(stderr, "%s: number of tokens in negative prompt = %zu\n", __func__, guidance_inp.size());
            for (int i = 0; i < (int) guidance_inp.size(); i++) {
                fprintf(stderr, "%6d -> '%s'\n", guidance_inp[i], llama_token_to_str(ctx, guidance_inp[i]));
            }
        }

        if (params.n_keep > 0) {
        fprintf(stderr, "%s: static prompt based on n_keep: '", __func__);
            for (int i = 0; i < params.n_keep; i++) {
                fprintf(stderr, "%s", llama_token_to_str(ctx, embd_inp[i]));
            }
            fprintf(stderr, "'\n");
        }
        fprintf(stderr, "\n");
    }

    if (params.interactive) {
#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__))
        struct sigaction sigint_action;
        sigint_action.sa_handler = sigint_handler;
        sigemptyset (&sigint_action.sa_mask);
        sigint_action.sa_flags = 0;
        sigaction(SIGINT, &sigint_action, NULL);
#elif defined (_WIN32)
        auto console_ctrl_handler = +[](DWORD ctrl_type) -> BOOL {
            return (ctrl_type == CTRL_C_EVENT) ? (sigint_handler(SIGINT), true) : false;
        };
        SetConsoleCtrlHandler(static_cast<PHANDLER_ROUTINE>(console_ctrl_handler), true);
#endif

        fprintf(stderr, "%s: interactive mode on.\n", __func__);

        if (params.antiprompt.size()) {
            for (auto antiprompt : params.antiprompt) {
                fprintf(stderr, "Reverse prompt: '%s'\n", antiprompt.c_str());
            }
        }

        if (!params.input_prefix.empty()) {
            fprintf(stderr, "Input prefix: '%s'\n", params.input_prefix.c_str());
        }

        if (!params.input_suffix.empty()) {
            fprintf(stderr, "Input suffix: '%s'\n", params.input_suffix.c_str());
        }
    }
    fprintf(stderr, "sampling: repeat_last_n = %d, repeat_penalty = %f, presence_penalty = %f, frequency_penalty = %f, top_k = %d, tfs_z = %f, top_p = %f, typical_p = %f, temp = %f, mirostat = %d, mirostat_lr = %f, mirostat_ent = %f\n",
            params.repeat_last_n, params.repeat_penalty, params.presence_penalty, params.frequency_penalty, params.top_k, params.tfs_z, params.top_p, params.typical_p, params.temp, params.mirostat, params.mirostat_eta, params.mirostat_tau);
    fprintf(stderr, "generate: n_ctx = %d, n_batch = %d, n_predict = %d, n_keep = %d\n", n_ctx, params.n_batch, params.n_predict, params.n_keep);
    fprintf(stderr, "\n\n");

    // TODO: replace with ring-buffer
    std::vector<llama_token> last_n_tokens(n_ctx);
    std::fill(last_n_tokens.begin(), last_n_tokens.end(), 0);

    if (params.interactive) {
        const char *control_message;
        if (con_st.multiline_input) {
            control_message = " - To return control to LLaMa, end your input with '\\'.\n"
                              " - To return control without starting a new line, end your input with '/'.\n";
        } else {
            control_message = " - Press Return to return control to LLaMa.\n"
                              " - To return control without starting a new line, end your input with '/'.\n"
                              " - If you want to submit another line, end your input with '\\'.\n";
        }
        fprintf(stderr, "== Running in interactive mode. ==\n"
#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__)) || defined (_WIN32)
               " - Press Ctrl+C to interject at any time.\n"
#endif
               "%s\n", control_message);

        is_interacting = params.interactive_first;
    }

    bool is_antiprompt        = false;
    bool input_echo           = true;
    bool need_to_save_session = !path_session.empty() && n_matching_session_tokens < embd_inp.size();

    int n_past             = 0;
    int n_remain           = params.n_predict;
    int n_consumed         = 0;
    int n_session_consumed = 0;
    int n_past_guidance    = 0;

    // the first thing we will do is to output the prompt, so set color accordingly
    console_set_color(con_st, CONSOLE_COLOR_PROMPT);

    std::vector<llama_token> embd;
    std::vector<llama_token> embd_guidance;

    // do one empty run to warm up the model
    {
        const std::vector<llama_token> tmp = { llama_token_bos(), };
        llama_eval(ctx, tmp.data(), tmp.size(), 0, params.n_threads);
        llama_reset_timings(ctx);
    }

    while ((n_remain != 0 && !is_antiprompt) || params.interactive) {
        // predict
        if (embd.size() > 0) {
            // Note: n_ctx - 4 here is to match the logic for commandline prompt handling via
            // --prompt or --file which uses the same value.
            auto max_embd_size = n_ctx - 4;
            // Ensure the input doesn't exceed the context size by truncating embd if necessary.
            if ((int)embd.size() > max_embd_size) {
                auto skipped_tokens = embd.size() - max_embd_size;
                console_set_color(con_st, CONSOLE_COLOR_ERROR);
                printf("<<input too long: skipped %zu token%s>>", skipped_tokens, skipped_tokens != 1 ? "s" : "");
                console_set_color(con_st, CONSOLE_COLOR_DEFAULT);
                fflush(stdout);
                embd.resize(max_embd_size);
            }

            // infinite text generation via context swapping
            // if we run out of context:
            // - take the n_keep first tokens from the original prompt (via n_past)
            // - take half of the last (n_ctx - n_keep) tokens and recompute the logits in batches
            if (n_past + (int) embd.size() + std::max<int>(0, guidance_offset) > n_ctx) {
                const int n_left = n_past - params.n_keep;

                // always keep the first token - BOS
                n_past = std::max(1, params.n_keep);
                n_past_guidance = std::max(1, params.n_keep + guidance_offset);

                // insert n_left/2 tokens at the start of embd from last_n_tokens
                embd.insert(embd.begin(), last_n_tokens.begin() + n_ctx - n_left/2 - embd.size(), last_n_tokens.end() - embd.size());

                // stop saving session if we run out of context
                path_session.clear();

                //printf("\n---\n");
                //printf("resetting: '");
                //for (int i = 0; i < (int) embd.size(); i++) {
                //    printf("%s", llama_token_to_str(ctx, embd[i]));
                //}
                //printf("'\n");
                //printf("\n---\n");
            }

            // try to reuse a matching prefix from the loaded session instead of re-eval (via n_past)
            if (n_session_consumed < (int) session_tokens.size()) {
                size_t i = 0;
                for ( ; i < embd.size(); i++) {
                    if (embd[i] != session_tokens[n_session_consumed]) {
                        session_tokens.resize(n_session_consumed);
                        break;
                    }

                    n_past++;
                    n_session_consumed++;

                    if (n_session_consumed >= (int) session_tokens.size()) {
                        ++i;
                        break;
                    }
                }
                if (i > 0) {
                    embd.erase(embd.begin(), embd.begin() + i);
                }
            }

            // evaluate tokens in batches
            // embd is typically prepared beforehand to fit within a batch, but not always

            if (ctx_guidance) {
                int input_size = 0;
                llama_token* input_buf = NULL;

                if (n_past_guidance < (int) guidance_inp.size()) {
                    // Guidance context should have the same data with these modifications:
                    //
                    // * Replace the initial prompt
                    // * Shift everything by guidance_offset
                    embd_guidance = guidance_inp;
                    if (embd.begin() + original_prompt_len < embd.end()) {
                        embd_guidance.insert(
                            embd_guidance.end(),
                            embd.begin() + original_prompt_len,
                            embd.end()
                        );
                    }

                    input_buf = embd_guidance.data();
                    input_size = embd_guidance.size();
                    //fprintf(stderr, "\n---------------------\n");
                    //for (int i = 0; i < (int) embd_guidance.size(); i++) {
                        //fprintf(stderr, "%s", llama_token_to_str(ctx, embd_guidance[i]));
                    //}
                    //fprintf(stderr, "\n---------------------\n");
                } else {
                    input_buf = embd.data();
                    input_size = embd.size();
                }

                for (int i = 0; i < input_size; i += params.n_batch) {
                    int n_eval = std::min(input_size - i, params.n_batch);
                    if (llama_eval(ctx_guidance, input_buf + i, n_eval, n_past_guidance, params.n_threads)) {
                        fprintf(stderr, "%s : failed to eval\n", __func__);
                        return 1;
                    }

                    n_past_guidance += n_eval;
                }
            }

            for (int i = 0; i < (int) embd.size(); i += params.n_batch) {
                int n_eval = (int) embd.size() - i;
                if (n_eval > params.n_batch) {
                    n_eval = params.n_batch;
                }
                if (llama_eval(ctx, &embd[i], n_eval, n_past, params.n_threads)) {
                    fprintf(stderr, "%s : failed to eval\n", __func__);
                    return 1;
                }
                n_past += n_eval;
            }

            if (embd.size() > 0 && !path_session.empty()) {
                session_tokens.insert(session_tokens.end(), embd.begin(), embd.end());
                n_session_consumed = session_tokens.size();
            }
        }

        embd.clear();
        embd_guidance.clear();

        if ((int) embd_inp.size() <= n_consumed && !is_interacting) {
            // out of user input, sample next token
            const float   temp            = params.temp;
            const int32_t top_k           = params.top_k <= 0 ? llama_n_vocab(ctx) : params.top_k;
            const float   top_p           = params.top_p;
            const float   tfs_z           = params.tfs_z;
            const float   typical_p       = params.typical_p;
            const int32_t repeat_last_n   = params.repeat_last_n < 0 ? n_ctx : params.repeat_last_n;
            const float   repeat_penalty  = params.repeat_penalty;
            const float   alpha_presence  = params.presence_penalty;
            const float   alpha_frequency = params.frequency_penalty;
            const int     mirostat        = params.mirostat;
            const float   mirostat_tau    = params.mirostat_tau;
            const float   mirostat_eta    = params.mirostat_eta;
            const bool    penalize_nl     = params.penalize_nl;

            // optionally save the session on first sample (for faster prompt loading next time)
            if (!path_session.empty() && need_to_save_session && !params.prompt_cache_ro) {
                need_to_save_session = false;
                llama_save_session_file(ctx, path_session.c_str(), session_tokens.data(), session_tokens.size());
            }

            llama_token id = 0;

            {
                auto logits  = llama_get_logits(ctx);
                auto n_vocab = llama_n_vocab(ctx);

                // Apply params.logit_bias map
                for (auto it = params.logit_bias.begin(); it != params.logit_bias.end(); it++) {
                    logits[it->first] += it->second;
                }

                std::vector<llama_token_data> candidates;
                candidates.reserve(n_vocab);
                for (llama_token token_id = 0; token_id < n_vocab; token_id++) {
                    candidates.emplace_back(llama_token_data{token_id, logits[token_id], 0.0f});
                }

                llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false };

                if (ctx_guidance) {
                    llama_sample_classifier_free_guidance(ctx, &candidates_p, ctx_guidance, params.cfg_scale, params.cfg_smooth_factor);
                }

                // Apply penalties
                float nl_logit = logits[llama_token_nl()];
                auto last_n_repeat = std::min(std::min((int)last_n_tokens.size(), repeat_last_n), n_ctx);
                llama_sample_repetition_penalty(ctx, &candidates_p,
                    last_n_tokens.data() + last_n_tokens.size() - last_n_repeat,
                    last_n_repeat, repeat_penalty);
                llama_sample_frequency_and_presence_penalties(ctx, &candidates_p,
                    last_n_tokens.data() + last_n_tokens.size() - last_n_repeat,
                    last_n_repeat, alpha_frequency, alpha_presence);
                if (!penalize_nl) {
                    logits[llama_token_nl()] = nl_logit;
                }

                if (temp <= 0) {
                    // Greedy sampling
                    id = llama_sample_token_greedy(ctx, &candidates_p);
                } else {
                    if (mirostat == 1) {
                        static float mirostat_mu = 2.0f * mirostat_tau;
                        const int mirostat_m = 100;
                        llama_sample_temperature(ctx, &candidates_p, temp);
                        id = llama_sample_token_mirostat(ctx, &candidates_p, mirostat_tau, mirostat_eta, mirostat_m, &mirostat_mu);
                    } else if (mirostat == 2) {
                        static float mirostat_mu = 2.0f * mirostat_tau;
                        llama_sample_temperature(ctx, &candidates_p, temp);
                        id = llama_sample_token_mirostat_v2(ctx, &candidates_p, mirostat_tau, mirostat_eta, &mirostat_mu);
                    } else {
                        // Temperature sampling
                        llama_sample_top_k(ctx, &candidates_p, top_k, 1);
                        llama_sample_tail_free(ctx, &candidates_p, tfs_z, 1);
                        llama_sample_typical(ctx, &candidates_p, typical_p, 1);
                        llama_sample_top_p(ctx, &candidates_p, top_p, 1);
                        llama_sample_temperature(ctx, &candidates_p, temp);
                        id = llama_sample_token(ctx, &candidates_p);
                    }
                }
                // printf("`%d`", candidates_p.size);

                last_n_tokens.erase(last_n_tokens.begin());
                last_n_tokens.push_back(id);
            }

            // replace end of text token with newline token when in interactive mode
            if (id == llama_token_eos() && params.interactive && !params.instruct) {
                id = llama_token_newline.front();
                if (params.antiprompt.size() != 0) {
                    // tokenize and inject first reverse prompt
                    const auto first_antiprompt = ::llama_tokenize(ctx, params.antiprompt.front(), false);
                    embd_inp.insert(embd_inp.end(), first_antiprompt.begin(), first_antiprompt.end());
                }
            }

            // add it to the context
            embd.push_back(id);

            // echo this to console
            input_echo = true;

            // decrement remaining sampling budget
            --n_remain;
        } else {
            // some user input remains from prompt or interaction, forward it to processing
            while ((int) embd_inp.size() > n_consumed) {
                embd.push_back(embd_inp[n_consumed]);
                last_n_tokens.erase(last_n_tokens.begin());
                last_n_tokens.push_back(embd_inp[n_consumed]);
                ++n_consumed;
                if ((int) embd.size() >= params.n_batch) {
                    break;
                }
            }
        }

        // display text
        if (input_echo) {
            for (auto id : embd) {
                printf("%s", llama_token_to_str(ctx, id));
            }
            fflush(stdout);
        }
        // reset color to default if we there is no pending user input
        if (input_echo && (int)embd_inp.size() == n_consumed) {
            console_set_color(con_st, CONSOLE_COLOR_DEFAULT);
        }

        // if not currently processing queued inputs;
        if ((int) embd_inp.size() <= n_consumed) {

            // check for reverse prompt
            if (params.antiprompt.size()) {
                std::string last_output;
                for (auto id : last_n_tokens) {
                    last_output += llama_token_to_str(ctx, id);
                }

                is_antiprompt = false;
                // Check if each of the reverse prompts appears at the end of the output.
                // If we're not running interactively, the reverse prompt might be tokenized with some following characters
                // so we'll compensate for that by widening the search window a bit.
                for (std::string & antiprompt : params.antiprompt) {
                    size_t extra_padding = params.interactive ? 0 : 2;
                    size_t search_start_pos = last_output.length() > static_cast<size_t>(antiprompt.length() + extra_padding)
                        ? last_output.length() - static_cast<size_t>(antiprompt.length() + extra_padding)
                        : 0;

                    if (last_output.find(antiprompt.c_str(), search_start_pos) != std::string::npos) {
                        if (params.interactive) {
                            is_interacting = true;
                            console_set_color(con_st, CONSOLE_COLOR_USER_INPUT);
                        }
                        is_antiprompt = true;
                        fflush(stdout);
                        break;
                    }
                }
            }

            if (n_past > 0 && is_interacting) {
                if (params.instruct) {
                    printf("\n> ");
                }

                std::string buffer;
                if (!params.input_prefix.empty()) {
                    buffer += params.input_prefix;
                    printf("%s", buffer.c_str());
                }

                std::string line;
                bool another_line = true;
                do {
                    another_line = console_readline(con_st, line);
                    buffer += line;
                } while (another_line);

                // done taking input, reset color
                console_set_color(con_st, CONSOLE_COLOR_DEFAULT);

                // Add tokens to embd only if the input buffer is non-empty
                // Entering a empty line lets the user pass control back
                if (buffer.length() > 1) {
                    // append input suffix if any
                    if (!params.input_suffix.empty()) {
                        buffer += params.input_suffix;
                        printf("%s", params.input_suffix.c_str());
                    }

                    // instruct mode: insert instruction prefix
                    if (params.instruct && !is_antiprompt) {
                        n_consumed = embd_inp.size();
                        embd_inp.insert(embd_inp.end(), inp_pfx.begin(), inp_pfx.end());
                    }

                    auto line_inp = ::llama_tokenize(ctx, buffer, false);
                    embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end());

                    // instruct mode: insert response suffix
                    if (params.instruct) {
                        embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end());
                    }

                    n_remain -= line_inp.size();
                }

                input_echo = false; // do not echo this again
            }

            if (n_past > 0) {
                is_interacting = false;
            }
        }

        // end of text token
        if (!embd.empty() && embd.back() == llama_token_eos()) {
            if (params.instruct) {
                is_interacting = true;
            } else {
                fprintf(stderr, " [end of text]\n");
                break;
            }
        }

        // In interactive mode, respect the maximum number of tokens and drop back to user input when reached.
        if (params.interactive && n_remain <= 0 && params.n_predict != -1) {
            n_remain = params.n_predict;
            is_interacting = true;
        }
    }

    if (!path_session.empty() && params.prompt_cache_all && !params.prompt_cache_ro) {
        fprintf(stderr, "\n%s: saving final output to session file '%s'\n", __func__, path_session.c_str());
        llama_save_session_file(ctx, path_session.c_str(), session_tokens.data(), session_tokens.size());
    }

    llama_print_timings(ctx);
    if (ctx_guidance) { llama_free(ctx_guidance); }
    llama_free(ctx);
    llama_free_model(model);

    llama_backend_free();

    return 0;
}