llama : more tokenizer fixes (#2810)

* tests : write a Python tokenizer test (wip)

* llama : prefix input text for tokenization with whitespace

* llama : distinguish pieces from decoded text + fix detokenization

* common : add comments

* examples : no longer manually add leading space when tokenizing

* tests : use Python to generate tokenizer tests for C++

* tests : add option to tokenize text files

ggml-ci

* tests : add test-tokenizer-1.py

* llama.cpp : fix LF token

* hellaswag : move the concat space for clarity

* tests : add falcon tests (py + cpp, currently do not pass Unicode)

ggml-ci

* common : temporary separate llama_detokenize calls for SPM and BPE

---------

Co-authored-by: klosax <131523366+klosax@users.noreply.github.com>

1 files changed, 36 insertions, 3 deletions

diff --git a/common/common.cpp b/common/common.cpp
index ff19ec4e..0d91a6a3 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -733,12 +733,12 @@ std::vector<llama_token> llama_tokenize(
     return result;
 }
 
-std::string llama_token_to_str(const struct llama_context * ctx, llama_token token) {
+std::string llama_token_to_piece(const struct llama_context * ctx, llama_token token) {
     std::vector<char> result(8, 0);
-    const int n_tokens = llama_token_to_str(ctx, token, result.data(), result.size());
+    const int n_tokens = llama_token_to_piece(ctx, token, result.data(), result.size());
     if (n_tokens < 0) {
         result.resize(-n_tokens);
-        int check = llama_token_to_str(ctx, token, result.data(), result.size());
+        int check = llama_token_to_piece(ctx, token, result.data(), result.size());
         GGML_ASSERT(check == -n_tokens);
     } else {
         result.resize(n_tokens);
@@ -746,3 +746,36 @@ std::string llama_token_to_str(const struct llama_context * ctx, llama_token tok
 
     return std::string(result.data(), result.size());
 }
+
+std::string llama_detokenize_spm(llama_context * ctx, const std::vector<llama_token> & tokens) {
+    const llama_token bos_id = llama_token_bos(ctx);
+
+    std::string piece;
+    std::string result;
+
+    for (size_t i = 0; i < tokens.size(); ++i) {
+        piece = llama_token_to_piece(ctx, tokens[i]);
+
+        // remove the leading space of the first non-BOS token
+        if (((tokens[0] == bos_id && i == 1) || (tokens[0] != bos_id && i == 0)) && piece[0] == ' ') {
+            piece = piece.substr(1);
+        }
+
+        result += piece;
+    }
+
+    return result;
+}
+
+std::string llama_detokenize_bpe(llama_context * ctx, const std::vector<llama_token> & tokens) {
+    std::string piece;
+    std::string result;
+
+    for (size_t i = 0; i < tokens.size(); ++i) {
+        piece = llama_token_to_piece(ctx, tokens[i]);
+
+        result += piece;
+    }
+
+    return result;
+}