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

15
examples/server/server.cpp
View file

@ -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));