schihei/llama2.c
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'master' into master

Browse Source
This commit is contained in:
Daniel Grittner
2023-08-06 19:55:43 +02:00
committed by GitHub
parent fcb4cdef8b a7a3aa09b8
commit 512f039d5d
2 changed files with 63 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+30 -20
View File
@@ -208,26 +208,36 @@ If your candidate PRs have elements of these it doesn't mean they won't get merg
## notable forks ## notable forks
- [llama2.rs](https://github.com/gaxler/llama2.rs) by @gaxler: a Rust port of this project - Rust
- [go-llama2](https://github.com/tmc/go-llama2) by @tmc: a Go port of this project - [llama2.rs](https://github.com/gaxler/llama2.rs) by @[gaxler](https://github.com/gaxler): a Rust port of this project
- [llama2.go](https://github.com/nikolaydubina/llama2.go) by @nikolaydubina: a Go port of this project - [llama2.rs](https://github.com/leo-du/llama2.rs) by @[leo-du](https://github.com/leo-du): A Rust port of this project
- [llama2.go](https://github.com/haormj/llama2.go) by @haormj: a Go port of this project - [llama2-rs](https://github.com/danielgrittner/llama2-rs) by @[danielgrittner](https://github.com/danielgrittner): a Rust port of this project
- [llama2.go](https://github.com/saracen/llama2.go) by @saracen: a Go port of this project - Go
- [llama2.c-android](https://github.com/Manuel030/llama2.c-android): by @Manuel030: adds Android binaries of this project - [go-llama2](https://github.com/tmc/go-llama2) by @[tmc](https://github.com/tmc): a Go port of this project
- [llama2.c-android-wrapper](https://github.com/celikin/llama2.c-android-wrapper): by @celikin: added JNI wrapper, PoC - [llama2.go](https://github.com/nikolaydubina/llama2.go) by @[nikolaydubina](https://github.com/nikolaydubina): a Go port of this project
- [llama2.cpp](https://github.com/leloykun/llama2.cpp) by @leloykun: a C++ port of this project - [llama2.go](https://github.com/haormj/llama2.go) by @[haormj](https://github.com/haormj): a Go port of this project
- [llama2.js](https://github.com/epicure/llama2.js) by @epicure: a JavaScript port of this project - [llama2.go](https://github.com/saracen/llama2.go) by @[saracen](https://github.com/saracen): a Go port of this project
- [llama2.zig](https://github.com/cgbur/llama2.zig) by @cgbur: A Zig port of this project - Android
- [llama2.zig](https://github.com/vodkaslime/llama2.zig) by @vodkaslime: a Zig port of this project - [llama2.c-android](https://github.com/Manuel030/llama2.c-android): by @[Manuel030](https://github.com/Manuel030): adds Android binaries of this project
- [llama2.jl](https://github.com/juvi21/llama2.jl) by @juvi21: a Julia port of this project - [llama2.c-android-wrapper](https://github.com/celikin/llama2.c-android-wrapper): by @[celikin](https://github.com/celikin): added JNI wrapper, PoC
- [llama2.c - Llama 2 Everywhere](https://github.com/trholding/llama2.c) by @trholding: Standalone, Bootable & Portable Binary Llama 2 - C++
- [llama2.rs](https://github.com/leo-du/llama2.rs) by @leo-du: A Rust port of this project - [llama2.cpp](https://github.com/leloykun/llama2.cpp) by @[leloykun](https://github.com/leloykun): a C++ port of this project
- [llama2.scala](https://github.com/jrudolph/llama2.scala) by @jrudolph: a Scala port of this project - JavaScript
- [llama2.c-emscripten](https://github.com/gohai/llama2.c-emscripten) by @gohai: Emscripten (JavaScript) port, based on @ggerganov's initial prototype - [llama2.js](https://github.com/epicure/llama2.js) by @[epicure](https://github.com/epicure): a JavaScript port of this project
- [llama2.java](https://github.com/mukel/llama2.java) by @mukel: a Java port of this project - [llama2.c-emscripten](https://github.com/gohai/llama2.c-emscripten) by @[gohai](https://github.com/gohai): Emscripten (JavaScript) port, based on @ggerganov's initial prototype
- [llama2.kt](https://github.com/madroidmaq/llama2.kt) by @madroidmaq: a Kotlin port of this project - Zig
- [llama2.zig](https://github.com/clebert/llama2.zig) by @clebert: a Zig port of this project - [llama2.zig](https://github.com/cgbur/llama2.zig) by @[cgbur](https://github.com/cgbur): A Zig port of this project
- [llama2-rs](https://github.com/danielgrittner/llama2-rs) by @danielgrittner: a Rust port of this project - [llama2.zig](https://github.com/vodkaslime/llama2.zig) by @[vodkaslime](https://github.com/vodkaslime): a Zig port of this project
- [llama2.zig](https://github.com/clebert/llama2.zig) by @[clebert](https://github.com/clebert): a Zig port of this project
- Julia
- [llama2.jl](https://github.com/juvi21/llama2.jl) by @[juvi21](https://github.com/juvi21): a Julia port of this project
- Scala
- [llama2.scala](https://github.com/jrudolph/llama2.scala) by @[jrudolph](https://github.com/jrudolph): a Scala port of this project
- Java
- [llama2.java](https://github.com/mukel/llama2.java) by @[mukel](https://github.com/mukel): a Java port of this project
- Kotlin
- [llama2.kt](https://github.com/madroidmaq/llama2.kt) by @[madroidmaq](https://github.com/madroidmaq): a Kotlin port of this project
- [llama2.c - Llama 2 Everywhere](https://github.com/trholding/llama2.c) by @[trholding](https://github.com/trholding): Standalone, Bootable & Portable Binary Llama 2
## unsorted todos ## unsorted todos
run.c
+33 -28
View File
@@ -99,7 +99,7 @@ void malloc_run_state(RunState* s, Config* p) {
if (!s->x || !s->xb || !s->xb2 || !s->hb || !s->hb2 || !s->q if (!s->x || !s->xb || !s->xb2 || !s->hb || !s->hb2 || !s->q
|| !s->k || !s->v || !s->att || !s->logits || !s->key_cache || !s->k || !s->v || !s->att || !s->logits || !s->key_cache
|| !s->value_cache || !s->probindex) { || !s->value_cache || !s->probindex) {
printf("malloc failed!\n"); fprintf(stderr, "malloc failed!\n");
exit(EXIT_FAILURE); exit(EXIT_FAILURE);
} }
} }
@@ -362,7 +362,7 @@ void bpe_encode(char *text, char **vocab, float *vocab_scores, int vocab_size, u
for (char *c = text; *c != '\0'; c++) { for (char *c = text; *c != '\0'; c++) {
sprintf(str_buffer, "%c", *c); sprintf(str_buffer, "%c", *c);
int id = str_lookup(str_buffer, vocab, vocab_size); int id = str_lookup(str_buffer, vocab, vocab_size);
if (id == -1) { printf("not good\n"); exit(EXIT_FAILURE); } if (id == -1) { fprintf(stderr, "not good\n"); exit(EXIT_FAILURE); }
tokens[*n_tokens] = id; tokens[*n_tokens] = id;
(*n_tokens)++; (*n_tokens)++;
} }
@@ -500,14 +500,14 @@ int sample_topp(float* probabilities, int n, float topp, ProbIndex* probindex) {
// int main // int main
void error_usage() { void error_usage() {
printf("Usage: run <checkpoint> [options]\n"); fprintf(stderr, "Usage: run <checkpoint> [options]\n");
printf("Example: run model.bin -n 256 -i \"Once upon a time\"\n"); fprintf(stderr, "Example: run model.bin -n 256 -i \"Once upon a time\"\n");
printf("Options:\n"); fprintf(stderr, "Options:\n");
printf(" -t <float> temperature, default 1.0\n"); fprintf(stderr, " -t <float> temperature, default 1.0\n");
printf(" -p <float> p value in top-p (nucleus) sampling. default 0.9, 0 = off\n"); fprintf(stderr, " -p <float> p value in top-p (nucleus) sampling. default 0.9, 0 = off\n");
printf(" -s <int> random seed, default time(NULL)\n"); fprintf(stderr, " -s <int> random seed, default time(NULL)\n");
printf(" -n <int> number of steps to run for, default 256. 0 = max_seq_len\n"); fprintf(stderr, " -n <int> number of steps to run for, default 256. 0 = max_seq_len\n");
printf(" -i <string> input prompt\n"); fprintf(stderr, " -i <string> input prompt\n");
exit(EXIT_FAILURE); exit(EXIT_FAILURE);
} }
@@ -536,7 +536,7 @@ int main(int argc, char *argv[]) {
else if (argv[i][1] == 'i') { prompt = argv[i + 1]; } else if (argv[i][1] == 'i') { prompt = argv[i + 1]; }
else { error_usage(); } else { error_usage(); }
} }
if(rng_seed == 0) { printf("Cannot use seed=0 because of the rng alg used\n"); return 1; } if(rng_seed == 0) { fprintf(stderr, "Cannot use seed=0 because of the rng alg used\n"); return 1; }
// read in the model.bin file // read in the model.bin file
Config config; Config config;
@@ -546,7 +546,7 @@ int main(int argc, char *argv[]) {
ssize_t file_size; // size of the checkpoint file in bytes ssize_t file_size; // size of the checkpoint file in bytes
{ {
FILE *file = fopen(checkpoint, "rb"); FILE *file = fopen(checkpoint, "rb");
if (!file) { printf("Couldn't open file %s\n", checkpoint); return 1; } if (!file) { fprintf(stderr, "Couldn't open file %s\n", checkpoint); return 1; }
// read in the config header // read in the config header
if (fread(&config, sizeof(Config), 1, file) != 1) { return 1; } if (fread(&config, sizeof(Config), 1, file) != 1) { return 1; }
// negative vocab size is hacky way of signaling unshared weights. bit yikes. // negative vocab size is hacky way of signaling unshared weights. bit yikes.
@@ -558,9 +558,9 @@ int main(int argc, char *argv[]) {
fclose(file); fclose(file);
// memory map the Transformer weights into the data pointer // memory map the Transformer weights into the data pointer
fd = open(checkpoint, O_RDONLY); // open in read only mode fd = open(checkpoint, O_RDONLY); // open in read only mode
if (fd == -1) { printf("open failed!\n"); return 1; } if (fd == -1) { fprintf(stderr, "open failed!\n"); return 1; }
data = mmap(NULL, file_size, PROT_READ, MAP_PRIVATE, fd, 0); data = mmap(NULL, file_size, PROT_READ, MAP_PRIVATE, fd, 0);
if (data == MAP_FAILED) { printf("mmap failed!\n"); return 1; } if (data == MAP_FAILED) { fprintf(stderr, "mmap failed!\n"); return 1; }
float* weights_ptr = data + sizeof(Config)/sizeof(float); float* weights_ptr = data + sizeof(Config)/sizeof(float);
checkpoint_init_weights(&weights, &config, weights_ptr, shared_weights); checkpoint_init_weights(&weights, &config, weights_ptr, shared_weights);
} }
@@ -573,14 +573,14 @@ int main(int argc, char *argv[]) {
unsigned int max_token_length; unsigned int max_token_length;
{ {
FILE *file = fopen("tokenizer.bin", "rb"); FILE *file = fopen("tokenizer.bin", "rb");
if (!file) { printf("couldn't load tokenizer.bin\n"); return 1; } if (!file) { fprintf(stderr, "couldn't load tokenizer.bin\n"); return 1; }
if (fread(&max_token_length, sizeof(int), 1, file) != 1) { printf("failed read\n"); return 1; } if (fread(&max_token_length, sizeof(int), 1, file) != 1) { fprintf(stderr, "failed read\n"); return 1; }
int len; int len;
for (int i = 0; i < config.vocab_size; i++) { for (int i = 0; i < config.vocab_size; i++) {
if (fread(vocab_scores + i, sizeof(float), 1, file) != 1) { printf("failed read\n"); return 1;} if (fread(vocab_scores + i, sizeof(float), 1, file) != 1) { fprintf(stderr, "failed read\n"); return 1;}
if (fread(&len, sizeof(int), 1, file) != 1) { printf("failed read\n"); return 1; } if (fread(&len, sizeof(int), 1, file) != 1) { fprintf(stderr, "failed read\n"); return 1; }
vocab[i] = (char *)malloc(len + 1); vocab[i] = (char *)malloc(len + 1);
if (fread(vocab[i], len, 1, file) != 1) { printf("failed read\n"); return 1; } if (fread(vocab[i], len, 1, file) != 1) { fprintf(stderr, "failed read\n"); return 1; }
vocab[i][len] = '\0'; // add the string terminating token vocab[i][len] = '\0'; // add the string terminating token
} }
fclose(file); fclose(file);
@@ -603,12 +603,12 @@ int main(int argc, char *argv[]) {
int next; // will store the next token in the sequence int next; // will store the next token in the sequence
int token = 1; // init with token 1 (=BOS), as done in Llama-2 sentencepiece tokenizer int token = 1; // init with token 1 (=BOS), as done in Llama-2 sentencepiece tokenizer
int pos = 0; // position in the sequence int pos = 0; // position in the sequence
printf("<s>\n"); // explicit print the initial BOS token for stylistic symmetry reasons
while (pos < steps) { while (pos < steps) {
// forward the transformer to get logits for the next token // forward the transformer to get logits for the next token
transformer(token, pos, &config, &state, &weights); transformer(token, pos, &config, &state, &weights);
// advance the state state machine
if(pos < num_prompt_tokens) { if(pos < num_prompt_tokens) {
// if we are still processing the input prompt, force the next prompt token // if we are still processing the input prompt, force the next prompt token
next = prompt_tokens[pos]; next = prompt_tokens[pos];
@@ -632,22 +632,27 @@ int main(int argc, char *argv[]) {
} }
} }
} }
pos++;
// following BOS token (1), sentencepiece decoder strips any leading whitespace (see PR #89) // data-dependent terminating condition: the BOS (1) token delimits sequences
if (next == 1) { break; }
// following BOS (1) token, sentencepiece decoder strips any leading whitespace (see PR #89)
char *token_str = (token == 1 && vocab[next][0] == ' ') ? vocab[next]+1 : vocab[next]; char *token_str = (token == 1 && vocab[next][0] == ' ') ? vocab[next]+1 : vocab[next];
printf("%s", token_str); printf("%s", token_str);
fflush(stdout); fflush(stdout);
// advance forward
token = next; token = next;
pos++;
// init our timer here because the first iteration is slow due to memmap // init the timer here because the first iteration can be slower
if (start == 0) { start = time_in_ms(); } if (start == 0) { start = time_in_ms(); }
} }
printf("\n");
// report achieved tok/s // report achieved tok/s (pos-1 because the timer starts after first iteration)
long end = time_in_ms(); if (pos > 1) {
printf("\nachieved tok/s: %f\n", (steps-1) / (double)(end-start)*1000); long end = time_in_ms();
fprintf(stderr, "achieved tok/s: %f\n", (pos-1) / (double)(end-start)*1000);
}
// memory and file handles cleanup // memory and file handles cleanup
free_run_state(&state); free_run_state(&state);