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/main/main.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/main/main.cpp')
-rw-r--r-- | examples/main/main.cpp | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/examples/main/main.cpp b/examples/main/main.cpp index 249fc2bb..1180734b 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -795,8 +795,8 @@ int main(int argc, char ** argv) { } } - // deal with end of text token in interactive mode - if (llama_sampling_last(ctx_sampling) == llama_token_eos(model)) { + // deal with end of generation tokens in interactive mode + if (llama_token_is_eog(model, llama_sampling_last(ctx_sampling))) { LOG("found EOS token\n"); if (params.interactive) { @@ -920,8 +920,8 @@ int main(int argc, char ** argv) { } } - // end of text token - if (!embd.empty() && embd.back() == llama_token_eos(model) && !(params.instruct || params.interactive || params.chatml)) { + // end of generation + if (!embd.empty() && llama_token_is_eog(model, embd.back()) && !(params.instruct || params.interactive || params.chatml)) { LOG_TEE(" [end of text]\n"); break; } |