From 11ea5c7d96f2c28e1c99659e08ec0a44574056e2 Mon Sep 17 00:00:00 2001 From: vvhg1 <94630311+vvhg1@users.noreply.github.com> Date: Tue, 10 Oct 2023 09:31:21 +0200 Subject: infill. : fix tokenization (#3508) * infill tokens correction * serverinfill tokens correction * removing any leading whitespace from infill suffix and removing leeading space token from suffix when params.escape * removing any leading whitespace from infill suffix and removing leeading space token from suffix when params.escape * only rm when params.escape, rm space if possible which is added back or rm added space token * only rm when params.escape, rm space if possible which is added back or rm added space token * Revert "only rm when params.escape, rm space if possible which is added back or rm added space token" This reverts commit 63ba0b621f21077c0e3bc6ba6a327534123cb738. * fix interactive prompt escaping and fix server infill leading space handling * rm unnecessary bool check --- examples/server/server.cpp | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'examples/server/server.cpp') diff --git a/examples/server/server.cpp b/examples/server/server.cpp index c53a6486..8c5318c6 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -344,9 +344,20 @@ struct llama_server_context void loadInfill() { - auto prefix_tokens = tokenize(params.input_prefix, true); // always add BOS - auto suffix_tokens = tokenize(params.input_suffix, true); // always add BOS + bool suff_rm_leading_spc = true; + if (params.input_suffix.find_first_of(" ") == 0 && params.input_suffix.size() > 1) { + params.input_suffix.erase(0, 1); + suff_rm_leading_spc = false; + } + + auto prefix_tokens = tokenize(params.input_prefix, false); + auto suffix_tokens = tokenize(params.input_suffix, false); + const int space_token = 29871; + if (suff_rm_leading_spc && suffix_tokens[0] == space_token) { + suffix_tokens.erase(suffix_tokens.begin()); + } prefix_tokens.insert(prefix_tokens.begin(), llama_token_prefix(ctx)); + prefix_tokens.insert(prefix_tokens.begin(), llama_token_bos(ctx)); // always add BOS prefix_tokens.insert(prefix_tokens.end(), llama_token_suffix(ctx)); prefix_tokens.insert(prefix_tokens.end(), suffix_tokens.begin(), suffix_tokens.end()); prefix_tokens.push_back(llama_token_middle(ctx)); -- cgit v1.2.3