File size: 6,203 Bytes
b664585
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#include "llama.h"
#include <cstdio>
#include <cstring>
#include <string>
#include <vector>

static void print_usage(int, char ** argv) {
    printf("\nexample usage:\n");
    printf("\n    %s -m model.gguf [-n n_predict] [-ngl n_gpu_layers] [prompt]\n", argv[0]);
    printf("\n");
}

int main(int argc, char ** argv) {
    // path to the model gguf file
    std::string model_path;
    // prompt to generate text from
    std::string prompt = "Hello my name is";
    // number of layers to offload to the GPU
    int ngl = 99;
    // number of tokens to predict
    int n_predict = 32;

    // parse command line arguments

    {
        int i = 1;
        for (; i < argc; i++) {
            if (strcmp(argv[i], "-m") == 0) {
                if (i + 1 < argc) {
                    model_path = argv[++i];
                } else {
                    print_usage(argc, argv);
                    return 1;
                }
            } else if (strcmp(argv[i], "-n") == 0) {
                if (i + 1 < argc) {
                    try {
                        n_predict = std::stoi(argv[++i]);
                    } catch (...) {
                        print_usage(argc, argv);
                        return 1;
                    }
                } else {
                    print_usage(argc, argv);
                    return 1;
                }
            } else if (strcmp(argv[i], "-ngl") == 0) {
                if (i + 1 < argc) {
                    try {
                        ngl = std::stoi(argv[++i]);
                    } catch (...) {
                        print_usage(argc, argv);
                        return 1;
                    }
                } else {
                    print_usage(argc, argv);
                    return 1;
                }
            } else {
                // prompt starts here
                break;
            }
        }
        if (model_path.empty()) {
            print_usage(argc, argv);
            return 1;
        }
        if (i < argc) {
            prompt = argv[i++];
            for (; i < argc; i++) {
                prompt += " ";
                prompt += argv[i];
            }
        }
    }

    // load dynamic backends

    ggml_backend_load_all();

    // initialize the model

    llama_model_params model_params = llama_model_default_params();
    model_params.n_gpu_layers = ngl;

    llama_model * model = llama_load_model_from_file(model_path.c_str(), model_params);

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

    // tokenize the prompt

    // find the number of tokens in the prompt
    const int n_prompt = -llama_tokenize(model, prompt.c_str(), prompt.size(), NULL, 0, true, true);

    // allocate space for the tokens and tokenize the prompt
    std::vector<llama_token> prompt_tokens(n_prompt);
    if (llama_tokenize(model, prompt.c_str(), prompt.size(), prompt_tokens.data(), prompt_tokens.size(), true, true) < 0) {
        fprintf(stderr, "%s: error: failed to tokenize the prompt\n", __func__);
        return 1;
    }

    // initialize the context

    llama_context_params ctx_params = llama_context_default_params();
    // n_ctx is the context size
    ctx_params.n_ctx = n_prompt + n_predict - 1;
    // n_batch is the maximum number of tokens that can be processed in a single call to llama_decode
    ctx_params.n_batch = n_prompt;
    // enable performance counters
    ctx_params.no_perf = false;

    llama_context * ctx = llama_new_context_with_model(model, ctx_params);

    if (ctx == NULL) {
        fprintf(stderr , "%s: error: failed to create the llama_context\n" , __func__);
        return 1;
    }

    // initialize the sampler

    auto sparams = llama_sampler_chain_default_params();
    sparams.no_perf = false;
    llama_sampler * smpl = llama_sampler_chain_init(sparams);

    llama_sampler_chain_add(smpl, llama_sampler_init_greedy());

    // print the prompt token-by-token

    for (auto id : prompt_tokens) {
        char buf[128];
        int n = llama_token_to_piece(model, id, buf, sizeof(buf), 0, true);
        if (n < 0) {
            fprintf(stderr, "%s: error: failed to convert token to piece\n", __func__);
            return 1;
        }
        std::string s(buf, n);
        printf("%s", s.c_str());
    }

    // prepare a batch for the prompt

    llama_batch batch = llama_batch_get_one(prompt_tokens.data(), prompt_tokens.size());

    // main loop

    const auto t_main_start = ggml_time_us();
    int n_decode = 0;
    llama_token new_token_id;

    for (int n_pos = 0; n_pos + batch.n_tokens < n_prompt + n_predict; ) {
        // evaluate the current batch with the transformer model
        if (llama_decode(ctx, batch)) {
            fprintf(stderr, "%s : failed to eval, return code %d\n", __func__, 1);
            return 1;
        }

        n_pos += batch.n_tokens;

        // sample the next token
        {
            new_token_id = llama_sampler_sample(smpl, ctx, -1);

            // is it an end of generation?
            if (llama_token_is_eog(model, new_token_id)) {
                break;
            }

            char buf[128];
            int n = llama_token_to_piece(model, new_token_id, buf, sizeof(buf), 0, true);
            if (n < 0) {
                fprintf(stderr, "%s: error: failed to convert token to piece\n", __func__);
                return 1;
            }
            std::string s(buf, n);
            printf("%s", s.c_str());
            fflush(stdout);

            // prepare the next batch with the sampled token
            batch = llama_batch_get_one(&new_token_id, 1);

            n_decode += 1;
        }
    }

    printf("\n");

    const auto t_main_end = ggml_time_us();

    fprintf(stderr, "%s: decoded %d tokens in %.2f s, speed: %.2f t/s\n",
            __func__, n_decode, (t_main_end - t_main_start) / 1000000.0f, n_decode / ((t_main_end - t_main_start) / 1000000.0f));

    fprintf(stderr, "\n");
    llama_perf_sampler_print(smpl);
    llama_perf_context_print(ctx);
    fprintf(stderr, "\n");

    llama_sampler_free(smpl);
    llama_free(ctx);
    llama_free_model(model);

    return 0;
}