We could use std::unordered_map over std::map (#305)

* Improve performance by changing std::map to std::unordered_map and std::map<id, token> id_to_token; to std::vector<token> id_to_token;

* fix last commit on gpt_vocab_init add vocab.id_to_token.resize(vocab.token_to_id.size());

* Removed include <map>

* Nest struct token score inside gpt_vocab

* renamed token to tok

main.cpp

@@ -9,7 +9,6 @@
 #include <cstring>
 #include <fstream>
 #include <iostream>
-#include <map>
 #include <string>
 #include <vector>
 
@@ -69,7 +68,7 @@ void set_console_state(console_state new_st)
 static const int EOS_TOKEN_ID = 2;
 
 // determine number of model parts based on the dimension
-static const std::map<int, int> LLAMA_N_PARTS = {
+static const std::unordered_map<int, int> LLAMA_N_PARTS = {
     { 4096, 1 },
     { 5120, 2 },
     { 6656, 4 },
@@ -123,7 +122,7 @@ struct llama_model {
 
     //
     struct ggml_context * ctx;
-    std::map<std::string, struct ggml_tensor *> tensors;
+    std::unordered_map<std::string, struct ggml_tensor *> tensors;
 };
 
 // load the model's weights from a file
@@ -208,6 +207,7 @@ bool llama_model_load(const std::string & fname, llama_model & model, llama_voca
     // load vocab
     {
         std::string word;
+        vocab.id_to_token.resize(model.hparams.n_vocab);
         std::vector<char> tmp(64);
 
         for (int i = 0; i < model.hparams.n_vocab; i++) {
@@ -227,8 +227,10 @@ bool llama_model_load(const std::string & fname, llama_model & model, llama_voca
             fin.read((char *) &score, sizeof(score));
 
             vocab.token_to_id[word] = i;
-            vocab.id_to_token[i] = word;
-            vocab.score[i] = score;
+
+            auto &tok_score = vocab.id_to_token[i];
+            tok_score.tok = word;
+            tok_score.score = score;
         }
     }
 
@@ -1028,7 +1030,7 @@ int main(int argc, char ** argv) {
     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], vocab.id_to_token.at(embd_inp[i]).c_str());
+        fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], vocab.id_to_token.at(embd_inp[i]).tok.c_str());
     }
     fprintf(stderr, "\n");
     if (params.interactive) {
@@ -1154,7 +1156,7 @@ int main(int argc, char ** argv) {
         // display text
         if (!input_noecho) {
             for (auto id : embd) {
-                printf("%s", vocab.id_to_token[id].c_str());
+                printf("%s", vocab.id_to_token[id].tok.c_str());
             }
             fflush(stdout);
         }
@@ -1169,7 +1171,7 @@ int main(int argc, char ** argv) {
             // check for reverse prompt
             std::string last_output;
             for (auto id : last_n_tokens) {
-                last_output += vocab.id_to_token[id];
+                last_output += vocab.id_to_token[id].tok;
             }
 
             // Check if each of the reverse prompts appears at the end of the output.

quantize.cpp

@@ -8,7 +8,6 @@
 #include <cstdio>
 #include <cstring>
 #include <fstream>
-#include <map>
 #include <string>
 #include <vector>
 #include <regex>
@@ -130,6 +129,7 @@ bool llama_model_quantize(const std::string & fname_inp, const std::string & fna
         }
 
         std::string word;
+        vocab.id_to_token.resize(n_vocab);
         for (int i = 0; i < n_vocab; i++) {
             uint32_t len;
             finp.read ((char *) &len, sizeof(len));
@@ -144,8 +144,10 @@ bool llama_model_quantize(const std::string & fname_inp, const std::string & fna
             fout.write((char *) &score, sizeof(score));
 
             vocab.token_to_id[word] = i;
-            vocab.id_to_token[i] = word;
-            vocab.score[i] = score;
+
+            auto &tok_score = vocab.id_to_token[i];
+            tok_score.tok = word;
+            tok_score.score = score;
         }
     }
 

utils.cpp

@@ -155,8 +155,8 @@ void replace(std::string & str, const std::string & needle, const std::string &
     }
 }
 
-std::map<std::string, int32_t> json_parse(const std::string & fname) {
-    std::map<std::string, int32_t> result;
+std::unordered_map<std::string, int32_t> json_parse(const std::string & fname) {
+    std::unordered_map<std::string, int32_t> result;
 
     // read file into string
     std::string json;
@@ -360,16 +360,16 @@ private:
             return;
         }
 
-        auto score = vocab_.score.find((*token).second);
-
-        if (score == vocab_.score.end()) {
+        if (static_cast<size_t>((*token).second) >= vocab_.id_to_token.size()) {
             return;
         }
 
+        const auto &tok_score = vocab_.id_to_token[(*token).second];
+
         llama_sp_bigram bigram;
         bigram.left = left;
         bigram.right = right;
-        bigram.score = (*score).second;
+        bigram.score = tok_score.score;
         bigram.size = text.size();
         work_queue_.push(bigram);
     }
@@ -393,6 +393,8 @@ bool llama_vocab_load(const std::string & fname, llama_vocab & vocab) {
     std::string word;
     std::vector<char> tmp(64);
 
+    vocab.id_to_token.resize(n_vocab);
+
     for (int i = 0; i < n_vocab; i++) {
         uint32_t len;
         fin.read((char *) &len, sizeof(len));
@@ -410,8 +412,10 @@ bool llama_vocab_load(const std::string & fname, llama_vocab & vocab) {
         fin.read((char *) &score, sizeof(score));
 
         vocab.token_to_id[word] = i;
-        vocab.id_to_token[i] = word;
-        vocab.score[i] = score;
+
+        auto &tok_score = vocab.id_to_token[i];
+        tok_score.tok = word;
+        tok_score.score = score;
     }
 
     return true;

utils.h

@@ -3,7 +3,7 @@
 #pragma once
 
 #include <string>
-#include <map>
+#include <unordered_map>
 #include <vector>
 #include <random>
 #include <thread>
@@ -65,15 +65,19 @@ struct llama_vocab {
     using id    = int32_t;
     using token = std::string;
 
-    std::map<token, id> token_to_id;
-    std::map<id, token> id_to_token;
-    std::map<id, float> score;
+    struct token_score {
+        token tok;
+        float score;
+    };
+
+    std::unordered_map<token, id> token_to_id;
+    std::vector<token_score> id_to_token;
 };
 
 void replace(std::string & str, const std::string & needle, const std::string & replacement);
 
 // poor-man's JSON parsing
-std::map<std::string, int32_t> json_parse(const std::string & fname);
+std::unordered_map<std::string, int32_t> json_parse(const std::string & fname);
 
 // TODO: temporary until #77 is merged, need this now for some tokenizer tests
 bool llama_vocab_load(const std::string & fname, llama_vocab & vocab);