How do I add my own prompt about llama2.c HOT 3 CLOSED

JANK SOLUTION 1

I added these code blocks, It only inferences one prompt at a time. And after retraining on Alpha-CoT (it is a poo poo dataset) my results are pretty incoherent. What data set would you retrain on?

// 'checkpoint' and 'input_sequence' are necessary args
    if (argc < 3) {
        printf("Usage: %s <checkpoint_file> <input_sequence> [temperature] [seed]\n", argv[0]);
        return 1;
    }
    checkpoint = argv[1];
    char *input_sequence_str = argv[2];
    // temperature is optional
    if (argc >= 4) {
        temperature = atof(argv[3]);
    }
    // seed is optional
    if (argc >= 5) {
        unsigned int seed = atoi(argv[4]);
        srand(seed);
    } else {
        time_t current_time; 
        time(&current_time);
        srand((unsigned int)current_time);
    }

    // call Python script to tokenize input sequence
    char command[2048];  // make sure this is large enough
    sprintf(command, "python pretokenize.py \"%s\"", input_sequence_str);
    FILE *pipe = popen(command, "r");
    if (!pipe) {
        printf("Unable to open pipe!");
        return 1;
    }

    // read tokenized input sequence from pipe
    int input_sequence[MAX_INPUT_LENGTH];
    int input_length = 0;
    while (fscanf(pipe, "%d", &input_sequence[input_length]) == 1) {
        input_length++;
        
    }
    //printf("input_length: %d", input_length);
    pclose(pipe);

Then to init the model state

// initialize the model's state with the input sequence
    int next;
    int pos = 0;

    
    for (int i = 0; i < input_length; i++) {
        transformer(input_sequence[i], pos, &config, &state, &weights);
        pos++;
        next = input_sequence[i];  // add this line

    }

    // start generating the output sequence after the input sequence
    while (pos < config.seq_len) {

        // forward the transformer to get logits for the next token
        transformer(next, pos, &config, &state, &weights);

Then I changed the run wrap file to work with input sequences. There isn't a run_wrap file anymore Im not sure how they are decoding the tokens. If you make this better please let me know.

EDIT: also this probably works better
#62 (comment)

from llama2.c.

卡顿解决方案 1

我添加了这些代码块，它一次只推断一个提示。在 Alpha-CoT（它是便便数据集）上重新训练后，我的结果非常不连贯。您将使用什么数据集进行重新训练？

// 'checkpoint' and 'input_sequence' are necessary args
    if (argc < 3) {
        printf("Usage: %s <checkpoint_file> <input_sequence> [temperature] [seed]\n", argv[0]);
        return 1;
    }
    checkpoint = argv[1];
    char *input_sequence_str = argv[2];
    // temperature is optional
    if (argc >= 4) {
        temperature = atof(argv[3]);
    }
    // seed is optional
    if (argc >= 5) {
        unsigned int seed = atoi(argv[4]);
        srand(seed);
    } else {
        time_t current_time; 
        time(&current_time);
        srand((unsigned int)current_time);
    }

    // call Python script to tokenize input sequence
    char command[2048];  // make sure this is large enough
    sprintf(command, "python pretokenize.py \"%s\"", input_sequence_str);
    FILE *pipe = popen(command, "r");
    if (!pipe) {
        printf("Unable to open pipe!");
        return 1;
    }

    // read tokenized input sequence from pipe
    int input_sequence[MAX_INPUT_LENGTH];
    int input_length = 0;
    while (fscanf(pipe, "%d", &input_sequence[input_length]) == 1) {
        input_length++;
        
    }
    //printf("input_length: %d", input_length);
    pclose(pipe);

然后初始化模型状态

// initialize the model's state with the input sequence
    int next;
    int pos = 0;

    
    for (int i = 0; i < input_length; i++) {
        transformer(input_sequence[i], pos, &config, &state, &weights);
        pos++;
        next = input_sequence[i];  // add this line

    }

    // start generating the output sequence after the input sequence
    while (pos < config.seq_len) {

        // forward the transformer to get logits for the next token
        transformer(next, pos, &config, &state, &weights);

然后我更改了运行包装文件以处理输入序列。不再有 run_wrap 文件我不确定他们如何解码令牌。如果你能做得更好，请告诉我。

编辑：这可能效果更好 #62（评论）

I don't have custom dataset, I want ti use open model to run directly. Your code is amazing, I will try it if it's merged

from llama2.c.

Now it supports prompt. Added on this commit

Usage details on the README

from llama2.c.