From b97bc3966e852adb626c90be64fd48282800f504 Mon Sep 17 00:00:00 2001 From: Pedro Cuenca Date: Sun, 21 Apr 2024 13:50:41 +0200 Subject: 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 --- examples/llama.swiftui/llama.cpp.swift/LibLlama.swift | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'examples/llama.swiftui') diff --git a/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift b/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift index c249291a..70c43a38 100644 --- a/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift +++ b/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift @@ -158,7 +158,7 @@ actor LlamaContext { new_token_id = llama_sample_token_greedy(context, &candidates_p) } - if new_token_id == llama_token_eos(model) || n_cur == n_len { + if llama_token_is_eog(model, new_token_id) || n_cur == n_len { print("\n") let new_token_str = String(cString: temporary_invalid_cchars + [0]) temporary_invalid_cchars.removeAll() -- cgit v1.2.3