From 1ba3df3de5f9f5c49a1d10083e8c30b3ed817e44 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Fri, 4 Oct 2024 11:54:32 +0300 Subject: [PATCH] rerank : use [SEP] token instead of [BOS] ggml-ci --- ci/run.sh | 3 ++- examples/server/server.cpp | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/ci/run.sh b/ci/run.sh index 7d241ecc0..7edae4f6e 100755 --- a/ci/run.sh +++ b/ci/run.sh @@ -751,7 +751,8 @@ function gg_run_rerank_tiny { model_f16="${path_models}/ggml-model-f16.gguf" - (time ./bin/llama-embedding --model ${model_f16} -p "what is panda?hi\nwhat is panda?it's a bear\nwhat is panda?The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China." --pooling rank --embd-normalize -1 --verbose-prompt) 2>&1 | tee -a $OUT/${ci}-rk-f16.log + # for this model, the SEP token is "" + (time ./bin/llama-embedding --model ${model_f16} -p "what is panda?hi\nwhat is panda?it's a bear\nwhat is panda?The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China." --pooling rank --embd-normalize -1 --verbose-prompt) 2>&1 | tee -a $OUT/${ci}-rk-f16.log # sample output # rerank score 0: 0.029 diff --git a/examples/server/server.cpp b/examples/server/server.cpp index f343cc252..13e54e501 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -2027,7 +2027,7 @@ struct server_context { continue; } - // prompt: querydoc + // prompt: [BOS]query[EOS][SEP]doc[EOS] prompt_tokens.clear(); prompt_tokens.push_back(llama_token_bos(model)); { @@ -2035,7 +2035,7 @@ struct server_context { prompt_tokens.insert(prompt_tokens.end(), part.begin(), part.end()); } prompt_tokens.push_back(llama_token_eos(model)); - prompt_tokens.push_back(llama_token_bos(model)); + prompt_tokens.push_back(llama_token_sep(model)); { const auto part = tokenize(slot.prompt[1], false); prompt_tokens.insert(prompt_tokens.end(), part.begin(), part.end());