gpt-3.5-turbo-0613· openai
Suzhen/CodeChat
Untitled conversation
- User
#include <stdio.h> #include <stdlib.h> #include <math.h> #include <time.h>”> #define HIDDEN_SIZE 100 #define VOCAB_SIZE 128 #define SEQ_LENGTH 25 #define LEARNING_RATE 1e-2 #define NUM_EPOCHS 1000 #define CLIP_VALUE 5 double Wxh[HIDDEN_SIZE][VOCAB_SIZE]; double Whh[HIDDEN_SIZE][HIDDEN_SIZE]; double Why[VOCAB_SIZE][HIDDEN_SIZE]; double bh[HIDDEN_SIZE]; double by[VOCAB_SIZE]; void initialize_parameters() { int i, j; for (i = 0; i < HIDDEN_SIZE; ++i) for (j = 0; j < VOCAB_SIZE; ++j) Wxh[i][j] = ((double)rand() / (double)RAND_MAX) * 0.01; for (i = 0; i < HIDDEN_SIZE; ++i) for (j = 0; j < HIDDEN_SIZE; ++j) Whh[i][j] = ((double)rand() / (double)RAND_MAX) * 0.01; for (i = 0; i < VOCAB_SIZE; ++i) for (j = 0; j < HIDDEN_SIZE; ++j) Why[i][j] = ((double)rand() / (double)RAND_MAX) * 0.01; for (i = 0; i < HIDDEN_SIZE; ++i) bh[i] = 0.0; for (i = 0; i < VOCAB_SIZE; ++i) by[i] = 0.0; } void clip(double *array, int len) { for (int i = 0; i < len; ++i) array[i] = array[i] > CLIP_VALUE ? CLIP_VALUE : array[i] < -CLIP_VALUE ? -CLIP_VALUE : array[i]; } double softmax(double *x, int size, int i) { int j; double sum_exp = 0.0; for (j = 0; j < size; ++j) { sum_exp += exp(x[j]); } return exp(x[i]) / sum_exp; } void one_hot_encode(char character, double *encoded) { int index = character; for (int i = 0; i < VOCAB_SIZE; ++i) { encoded[i] = (i == index) ? 1.0 : 0.0; } } char one_hot_decode(double *encoded) { int index = 0; double max_val = encoded[0]; for (int i = 1; i < VOCAB_SIZE; ++i) { if (encoded[i] > max_val) { index = i; max_val = encoded[i]; } } return (char)index; }Given the above C code, continue the implementation of a CharRNN. Implement the forward pass function, given the following function prototype:
void forward (char *input, char *output /same length as input (= SEQ_LENGTH)/, double *hprev);
- Assistant
void forward (char *input, char *output /*same length as input (= SEQ_LENGTH)*/, double *hprev) { double x[HIDDEN_SIZE][SEQ_LENGTH][VOCAB_SIZE]; double h[HIDDEN_SIZE][SEQ_LENGTH + 1]; double y[VOCAB_SIZE][SEQ_LENGTH]; // Initialize h with hprev for (int i = 0; i < HIDDEN_SIZE; ++i) { h[i][0] = hprev[i]; } // Forward pass for (int t = 0; t < SEQ_LENGTH; ++t) { // One-hot encoding of input character double input_encoded[VOCAB_SIZE]; one_hot_encode(input[t], input_encoded); // Update hidden state for (int i = 0; i < HIDDEN_SIZE; ++i) { double sum = 0.0; for (int j = 0; j < VOCAB_SIZE; ++j) { sum += Wxh[i][j] * input_encoded[j]; } for (int j = 0; j < HIDDEN_SIZE; ++j) { sum += Whh[i][j] * h[j][t]; } h[i][t + 1] = tanh(sum + bh[i]); } // Compute output probabilities for (int i = 0; i < VOCAB_SIZE; ++i) { double sum = 0.0; for (int j = 0; j < HIDDEN_SIZE; ++j) { sum += Why[i][j] * h[j][t + 1]; } y[i][t] = softmax(sum + by[i], VOCAB_SIZE, i); } // Sample the next character based on output probabilities output[t] = one_hot_decode(y[:,t]); } // Update hprev with the last hidden state for (int i = 0; i < HIDDEN_SIZE; ++i) { hprev[i] = h[i][SEQ_LENGTH]; } }
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.