vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

infill. : fix tokenization (#3508)

Browse source 
* 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 63ba0b621f.

* fix interactive prompt escaping and fix server infill leading space handling

* rm unnecessary bool check
This commit is contained in:
vvhg1 2023-10-10 09:31:21 +02:00 • committed by GitHub
parent 95bd60a0a6
commit 11ea5c7d96
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 46 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

37
examples/infill/infill.cpp
View file

@ -233,10 +233,22 @@ int main(int argc, char ** argv) {
const bool add_bos = llama_vocab_type(model) == LLAMA_VOCAB_TYPE_SPM;
LOG("add_bos: %d\n", add_bos);
bool suff_rm_leading_spc = params.escape;
if (suff_rm_leading_spc && params.input_suffix.find_first_of(" ") == 0 && params.input_suffix.size() > 1) {
params.input_suffix.erase(0, 1);
suff_rm_leading_spc = false;
}
std::vector<llama_token> embd_inp;
std::vector<llama_token> inp_pfx = ::llama_tokenize(ctx, params.input_prefix, add_bos);
std::vector<llama_token> inp_sfx = ::llama_tokenize(ctx, params.input_suffix, add_bos);
std::vector<llama_token> inp_pfx = ::llama_tokenize(ctx, params.input_prefix, false);
std::vector<llama_token> inp_sfx = ::llama_tokenize(ctx, params.input_suffix, false);
const int space_token = 29871;
if (suff_rm_leading_spc && inp_sfx[0] == space_token) {
inp_sfx.erase(inp_sfx.begin());
}
inp_pfx.insert(inp_pfx.begin(), llama_token_prefix(ctx));
if (add_bos) {
inp_pfx.insert(inp_pfx.begin(), llama_token_bos(ctx));
}
inp_sfx.insert(inp_sfx.begin(), llama_token_suffix(ctx));
embd_inp = inp_pfx;
embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end());
@ -627,10 +639,27 @@ int main(int argc, char ** argv) {
buffer.clear();
// done taking input, reset color
console::set_display(console::reset);
if (params.escape) {
//process escape sequences, for the initial prompt this is done in common.cpp when we load the params, but for the interactive mode we need to do it here
process_escapes(params.input_prefix);
process_escapes(params.input_suffix);
}
suff_rm_leading_spc = params.escape;
if (suff_rm_leading_spc && params.input_suffix.find_first_of(" ") == 0 && params.input_suffix.size() > 1) {
params.input_suffix.erase(0, 1);
suff_rm_leading_spc = false;
}
// tokenize new prefix and suffix
std::vector<llama_token> inp_pfx = ::llama_tokenize(ctx, params.input_prefix, add_bos);
std::vector<llama_token> inp_sfx = ::llama_tokenize(ctx, params.input_suffix, add_bos);
std::vector<llama_token> inp_pfx = ::llama_tokenize(ctx, params.input_prefix, false);
std::vector<llama_token> inp_sfx = ::llama_tokenize(ctx, params.input_suffix, false);
if (suff_rm_leading_spc && inp_sfx[0] == space_token) {
inp_sfx.erase(inp_sfx.begin());
}
inp_pfx.insert(inp_pfx.begin(), llama_token_prefix(ctx));
if (add_bos) {
inp_pfx.insert(inp_pfx.begin(), llama_token_bos(ctx));
}
inp_sfx.insert(inp_sfx.begin(), llama_token_suffix(ctx));
embd_inp = inp_pfx;
embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end());