Overhaul the examples structure
- main -> examples - utils -> examples (renamed to "common") - quantize -> examples - separate tools for "perplexity" and "embedding" Hope I didn't break something !pull/420/head^2 master-a316a42
parent
ecbe466a36
commit
a316a425d0
@ -0,0 +1,36 @@
|
||||
# dependencies
|
||||
|
||||
find_package(Threads REQUIRED)
|
||||
|
||||
# third-party
|
||||
|
||||
# ...
|
||||
|
||||
# common
|
||||
|
||||
set(TARGET common)
|
||||
|
||||
add_library(${TARGET} OBJECT
|
||||
common.h
|
||||
common.cpp
|
||||
)
|
||||
|
||||
if (BUILD_SHARED_LIBS)
|
||||
set_target_properties(${TARGET} PROPERTIES POSITION_INDEPENDENT_CODE ON)
|
||||
endif()
|
||||
|
||||
target_include_directories(${TARGET} PUBLIC .)
|
||||
target_compile_features(${TARGET} PUBLIC cxx_std_11)
|
||||
target_link_libraries(${TARGET} PRIVATE llama)
|
||||
|
||||
# examples
|
||||
|
||||
include_directories(${CMAKE_CURRENT_SOURCE_DIR})
|
||||
|
||||
if (EMSCRIPTEN)
|
||||
else()
|
||||
add_subdirectory(main)
|
||||
add_subdirectory(quantize)
|
||||
add_subdirectory(perplexity)
|
||||
add_subdirectory(embedding)
|
||||
endif()
|
@ -1,6 +1,6 @@
|
||||
#include "ggml.h"
|
||||
#include "common.h"
|
||||
|
||||
#include "utils.h"
|
||||
#include "ggml.h"
|
||||
|
||||
#include <cassert>
|
||||
#include <cstring>
|
@ -0,0 +1,4 @@
|
||||
set(TARGET embedding)
|
||||
add_executable(${TARGET} embedding.cpp)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
@ -0,0 +1,3 @@
|
||||
# embedding
|
||||
|
||||
TODO
|
@ -0,0 +1,106 @@
|
||||
#include "common.h"
|
||||
#include "llama.h"
|
||||
|
||||
#include <cassert>
|
||||
#include <cinttypes>
|
||||
#include <cmath>
|
||||
#include <cstdio>
|
||||
#include <cstring>
|
||||
#include <fstream>
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
int main(int argc, char ** argv) {
|
||||
gpt_params params;
|
||||
params.model = "models/llama-7B/ggml-model.bin";
|
||||
|
||||
if (gpt_params_parse(argc, argv, params) == false) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
params.embedding = true;
|
||||
|
||||
if (params.n_ctx > 2048) {
|
||||
fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);"
|
||||
"expect poor results\n", __func__, params.n_ctx);
|
||||
}
|
||||
|
||||
if (params.seed <= 0) {
|
||||
params.seed = time(NULL);
|
||||
}
|
||||
|
||||
fprintf(stderr, "%s: seed = %d\n", __func__, params.seed);
|
||||
|
||||
std::mt19937 rng(params.seed);
|
||||
if (params.random_prompt) {
|
||||
params.prompt = gpt_random_prompt(rng);
|
||||
}
|
||||
|
||||
llama_context * ctx;
|
||||
|
||||
// load the model
|
||||
{
|
||||
auto lparams = llama_context_default_params();
|
||||
|
||||
lparams.n_ctx = params.n_ctx;
|
||||
lparams.n_parts = params.n_parts;
|
||||
lparams.seed = params.seed;
|
||||
lparams.f16_kv = params.memory_f16;
|
||||
lparams.logits_all = params.perplexity;
|
||||
lparams.use_mlock = params.use_mlock;
|
||||
lparams.embedding = params.embedding;
|
||||
|
||||
ctx = llama_init_from_file(params.model.c_str(), lparams);
|
||||
|
||||
if (ctx == NULL) {
|
||||
fprintf(stderr, "%s: error: failed to load model '%s'\n", __func__, params.model.c_str());
|
||||
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());
|
||||
}
|
||||
|
||||
int n_past = 0;
|
||||
|
||||
// Add a space in front of the first character to match OG llama tokenizer behavior
|
||||
params.prompt.insert(0, 1, ' ');
|
||||
|
||||
// tokenize the prompt
|
||||
auto embd_inp = ::llama_tokenize(ctx, params.prompt, 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]));
|
||||
}
|
||||
fprintf(stderr, "\n");
|
||||
}
|
||||
|
||||
if (params.embedding){
|
||||
if (embd_inp.size() > 0) {
|
||||
if (llama_eval(ctx, embd_inp.data(), embd_inp.size(), n_past, params.n_threads)) {
|
||||
fprintf(stderr, "%s : failed to eval\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
|
||||
const auto embeddings = llama_get_embeddings(ctx);
|
||||
|
||||
// TODO: print / use the embeddings
|
||||
}
|
||||
|
||||
llama_print_timings(ctx);
|
||||
llama_free(ctx);
|
||||
|
||||
return 0;
|
||||
}
|
@ -0,0 +1,4 @@
|
||||
set(TARGET main)
|
||||
add_executable(${TARGET} main.cpp)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
@ -0,0 +1,3 @@
|
||||
# main
|
||||
|
||||
TODO
|
@ -0,0 +1,4 @@
|
||||
set(TARGET perplexity)
|
||||
add_executable(${TARGET} perplexity.cpp)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
@ -0,0 +1,3 @@
|
||||
# perplexity
|
||||
|
||||
TODO
|
@ -0,0 +1,146 @@
|
||||
#include "common.h"
|
||||
#include "llama.h"
|
||||
|
||||
#include <cassert>
|
||||
#include <cinttypes>
|
||||
#include <cmath>
|
||||
#include <cstdio>
|
||||
#include <cstring>
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
std::vector<double> softmax(const std::vector<float>& logits) {
|
||||
std::vector<double> probs(logits.size());
|
||||
float max_logit = logits[0];
|
||||
for (float v : logits) max_logit = std::max(max_logit, v);
|
||||
double sum_exp = 0.0;
|
||||
for (size_t i = 0; i < logits.size(); i++) {
|
||||
// Subtract the maximum logit value from the current logit value for numerical stability
|
||||
float logit = logits[i] - max_logit;
|
||||
double exp_logit = std::exp(logit);
|
||||
sum_exp += exp_logit;
|
||||
probs[i] = exp_logit;
|
||||
}
|
||||
for (size_t i = 0; i < probs.size(); i++) probs[i] /= sum_exp;
|
||||
return probs;
|
||||
}
|
||||
|
||||
void perplexity(llama_context * ctx, const gpt_params & params) {
|
||||
// Download: https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-2-raw-v1.zip?ref=salesforce-research
|
||||
// Run `./main --perplexity -m models/7B/ggml-model-q4_0.bin -f wiki.test.raw`
|
||||
// Output: `perplexity: 13.5106 [114/114]`
|
||||
auto tokens = ::llama_tokenize(ctx, params.prompt, true);
|
||||
|
||||
int count = 0;
|
||||
double nll = 0.0;
|
||||
int seq_count = tokens.size() / params.n_ctx;
|
||||
|
||||
fprintf(stderr, "%s : calculating perplexity over %d chunks\n", __func__, seq_count);
|
||||
|
||||
for (int i = 0; i < seq_count; ++i) {
|
||||
int start = i * params.n_ctx;
|
||||
int end = start + params.n_ctx - 1;
|
||||
std::vector<llama_token> embd(tokens.begin() + start, tokens.begin() + end);
|
||||
auto start_t = std::chrono::high_resolution_clock::now();
|
||||
if (llama_eval(ctx, embd.data(), embd.size(), 0, params.n_threads)) {
|
||||
fprintf(stderr, "%s : failed to eval\n", __func__);
|
||||
return;
|
||||
}
|
||||
auto end_t = std::chrono::high_resolution_clock::now();
|
||||
if (i == 0) {
|
||||
double seconds = std::chrono::duration<double>(end_t - start_t).count();
|
||||
printf("%.2f seconds per pass - ETA %.2f hours\n", seconds, (seconds * seq_count) / (60.0*60.0));
|
||||
}
|
||||
// We get the logits for all the tokens in the context window (params.n_ctx)
|
||||
// from llama_eval above. Now, based on https://huggingface.co/docs/transformers/perplexity,
|
||||
// calculate the perplexity over the last half the window (so the model always has
|
||||
// some context to predict the token).
|
||||
//
|
||||
// We rely on the fact that attention in the forward pass only looks at previous
|
||||
// tokens here, so the logits returned for each token are an accurate representation
|
||||
// of what the model would have predicted at that point.
|
||||
//
|
||||
// Example, we have a context window of 512, we will compute perplexity for each of the
|
||||
// last 256 tokens. Then, we split the input up into context window size chunks to
|
||||
// process the entire prompt.
|
||||
|
||||
auto logits = llama_get_logits(ctx);
|
||||
for (int j = params.n_ctx / 2; j < params.n_ctx - 1; ++j) {
|
||||
// Calculate probability of next token, given the previous ones.
|
||||
int n_vocab = llama_n_vocab(ctx);
|
||||
std::vector<float> tok_logits(
|
||||
logits + j * n_vocab,
|
||||
logits + (j + 1) * n_vocab);
|
||||
double prob = softmax(tok_logits)[tokens[start + j + 1]];
|
||||
nll += -std::log(prob);
|
||||
++count;
|
||||
}
|
||||
// perplexity is e^(average negative log-likelihood)
|
||||
printf("[%d]%.4lf,", i + 1, std::exp(nll / count));
|
||||
fflush(stdout);
|
||||
}
|
||||
printf("\n");
|
||||
}
|
||||
|
||||
int main(int argc, char ** argv) {
|
||||
gpt_params params;
|
||||
params.model = "models/llama-7B/ggml-model.bin";
|
||||
|
||||
if (gpt_params_parse(argc, argv, params) == false) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
params.perplexity = true;
|
||||
|
||||
if (params.n_ctx > 2048) {
|
||||
fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);"
|
||||
"expect poor results\n", __func__, params.n_ctx);
|
||||
}
|
||||
|
||||
if (params.seed <= 0) {
|
||||
params.seed = time(NULL);
|
||||
}
|
||||
|
||||
fprintf(stderr, "%s: seed = %d\n", __func__, params.seed);
|
||||
|
||||
std::mt19937 rng(params.seed);
|
||||
if (params.random_prompt) {
|
||||
params.prompt = gpt_random_prompt(rng);
|
||||
}
|
||||
|
||||
llama_context * ctx;
|
||||
|
||||
// load the model
|
||||
{
|
||||
auto lparams = llama_context_default_params();
|
||||
|
||||
lparams.n_ctx = params.n_ctx;
|
||||
lparams.n_parts = params.n_parts;
|
||||
lparams.seed = params.seed;
|
||||
lparams.f16_kv = params.memory_f16;
|
||||
lparams.logits_all = params.perplexity;
|
||||
lparams.use_mlock = params.use_mlock;
|
||||
lparams.embedding = params.embedding;
|
||||
|
||||
ctx = llama_init_from_file(params.model.c_str(), lparams);
|
||||
|
||||
if (ctx == NULL) {
|
||||
fprintf(stderr, "%s: error: failed to load model '%s'\n", __func__, params.model.c_str());
|
||||
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());
|
||||
}
|
||||
|
||||
perplexity(ctx, params);
|
||||
|
||||
llama_print_timings(ctx);
|
||||
llama_free(ctx);
|
||||
|
||||
return 0;
|
||||
}
|
@ -0,0 +1,4 @@
|
||||
set(TARGET quantize)
|
||||
add_executable(${TARGET} quantize.cpp)
|
||||
target_link_libraries(${TARGET} PRIVATE llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
@ -0,0 +1,3 @@
|
||||
# quantize
|
||||
|
||||
TODO
|
Loading…
Reference in New Issue