Skip to content

vocab : add special infill tokens for CodeLlama #11850

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 31, 2025
Merged

vocab : add special infill tokens for CodeLlama #11850

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2dd670e
vocab : add special infill tokens for CodeLlama
danbev Feb 13, 2025
5bcdbd0
squash! vocab : add special infill tokens for CodeLlama
danbev Mar 31, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions src/llama-vocab.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1801,6 +1801,7 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
|| t.first == "<fim-prefix>"
|| t.first == "<｜fim▁begin｜>" // DeepSeek
|| t.first == "<PRE>"
|| t.first == "▁<PRE>" // CodeLlama
) {
special_fim_pre_id = t.second;
if ((id_to_token[t.second].attr & LLAMA_TOKEN_ATTR_CONTROL) == 0) {
Expand All @@ -1818,6 +1819,7 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
|| t.first == "<fim-suffix>"
|| t.first == "<｜fim▁hole｜>" // DeepSeek
|| t.first == "<SUF>"
|| t.first == "▁<SUF>" // CodeLlama
) {
special_fim_suf_id = t.second;
if ((id_to_token[t.second].attr & LLAMA_TOKEN_ATTR_CONTROL) == 0) {
Expand All @@ -1835,6 +1837,7 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
|| t.first == "<fim-middle>"
|| t.first == "<｜fim▁end｜>" // DeepSeek
|| t.first == "<MID>"
|| t.first == "▁<MID>" // CodeLlama
) {
special_fim_mid_id = t.second;
if ((id_to_token[t.second].attr & LLAMA_TOKEN_ATTR_CONTROL) == 0) {
Expand Down
Loading