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/llava | |
| 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/llava')
| -rw-r--r-- | examples/llava/llava-cli.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/examples/llava/llava-cli.cpp b/examples/llava/llava-cli.cpp index 75948806..50dac4ca 100644 --- a/examples/llava/llava-cli.cpp +++ b/examples/llava/llava-cli.cpp @@ -45,7 +45,7 @@ static const char * sample(struct llama_sampling_context * ctx_sampling, const llama_token id = llama_sampling_sample(ctx_sampling, ctx_llama, NULL); llama_sampling_accept(ctx_sampling, ctx_llama, id, true); static std::string ret; - if (id == llama_token_eos(llama_get_model(ctx_llama))) { + if (llama_token_is_eog(llama_get_model(ctx_llama), id)) { ret = "</s>"; } else { ret = llama_token_to_piece(ctx_llama, id); |