diff options
| author | Pedro Cuenca <pedro@huggingface.co> | 2024-04-21 13:50:41 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-21 14:50:41 +0300 |
| commit | b97bc3966e852adb626c90be64fd48282800f504 (patch) | |
| tree | 178656d15821205889fa03ec603c7327facbb265 /examples/infill/infill.cpp | |
| parent | b8109bc0139f15a5b321909f47510b89dca47ffc (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/infill/infill.cpp')
| -rw-r--r-- | examples/infill/infill.cpp | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/examples/infill/infill.cpp b/examples/infill/infill.cpp index c69dcd06..afac145f 100644 --- a/examples/infill/infill.cpp +++ b/examples/infill/infill.cpp @@ -586,7 +586,7 @@ int main(int argc, char ** argv) { // deal with eot token in infill mode if ((llama_sampling_last(ctx_sampling) == llama_token_eot(model) || is_interacting) && params.interactive){ - if(is_interacting && !params.interactive_first) { + if (is_interacting && !params.interactive_first) { // print an eot token printf("%s", llama_token_to_piece(ctx, llama_token_eot(model)).c_str()); } @@ -651,8 +651,8 @@ int main(int argc, char ** argv) { // LOG_TEE("took new input\n"); is_interacting = false; } - // deal with end of text token in interactive mode - else if (llama_sampling_last(ctx_sampling) == llama_token_eos(model)) { + // deal with end of generation tokens in interactive mode + else if (llama_token_is_eog(model, llama_sampling_last(ctx_sampling))) { LOG("found EOS token\n"); if (params.interactive) { @@ -731,8 +731,8 @@ int main(int argc, char ** argv) { } } - // end of text token - if (!embd.empty() && embd.back() == llama_token_eos(model) && !params.interactive) { + // end of generation + if (!embd.empty() && llama_token_is_eog(model, embd.back()) && !params.interactive) { break; } |