summaryrefslogtreecommitdiff
path: root/examples/lookup
diff options
context:
space:
mode:
authorPedro Cuenca <pedro@huggingface.co>2024-04-21 13:50:41 +0200
committerGitHub <noreply@github.com>2024-04-21 14:50:41 +0300
commitb97bc3966e852adb626c90be64fd48282800f504 (patch)
tree178656d15821205889fa03ec603c7327facbb265 /examples/lookup
parentb8109bc0139f15a5b321909f47510b89dca47ffc (diff)
llama : support Llama 3 HF conversion (#6745)
* Support Llama 3 conversion The tokenizer is BPE. * style * Accept suggestion Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com> * llama : add llama_token_is_eog() ggml-ci * llama : auto-detect more EOT tokens when missing in KV data * convert : replacing EOS token is a hack * llama : fix codegemma EOT token + add TODOs * llama : fix model type string for 8B model --------- Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'examples/lookup')
-rw-r--r--examples/lookup/lookup.cpp2
1 files changed, 1 insertions, 1 deletions
diff --git a/examples/lookup/lookup.cpp b/examples/lookup/lookup.cpp
index 65ed408a..9526e898 100644
--- a/examples/lookup/lookup.cpp
+++ b/examples/lookup/lookup.cpp
@@ -141,7 +141,7 @@ int main(int argc, char ** argv){
printf("%s", token_str.c_str());
}
- if (id == llama_token_eos(model)) {
+ if (llama_token_is_eog(model, id)) {
has_eos = true;
}