From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 From: Michael Yang Date: Mon, 16 Sep 2024 15:53:13 -0700 Subject: [PATCH] pretokenizer --- src/llama.cpp | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/src/llama.cpp b/src/llama.cpp index 4c0a1bb6..800dfb95 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -6287,16 +6287,7 @@ static void llm_load_vocab( if (vocab.type == LLAMA_VOCAB_TYPE_BPE) { vocab.tokenizer_add_space_prefix = false; vocab.tokenizer_clean_spaces = true; - if (tokenizer_pre.empty()) { - LLAMA_LOG_WARN("%s: missing pre-tokenizer type, using: 'default'\n", __func__); - LLAMA_LOG_WARN("%s: \n", __func__); - LLAMA_LOG_WARN("%s: ************************************ \n", __func__); - LLAMA_LOG_WARN("%s: GENERATION QUALITY WILL BE DEGRADED! \n", __func__); - LLAMA_LOG_WARN("%s: CONSIDER REGENERATING THE MODEL \n", __func__); - LLAMA_LOG_WARN("%s: ************************************ \n", __func__); - LLAMA_LOG_WARN("%s: \n", __func__); - vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT; - } else if (tokenizer_pre == "default") { + if (tokenizer_pre == "default") { vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT; } else if ( tokenizer_pre == "llama3" || @@ -6398,7 +6389,8 @@ static void llm_load_vocab( vocab.tokenizer_add_bos = true; vocab.tokenizer_clean_spaces = false; } else { - throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str())); + LLAMA_LOG_WARN("%s: missing or unrecognized pre-tokenizer type, using: 'default'\n", __func__); + vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT; } } else if (vocab.type == LLAMA_VOCAB_TYPE_SPM) { vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;