From 201cc11afa0a1950e1f632390b2ac6c937a0d8f0 Mon Sep 17 00:00:00 2001 From: liuwei-git <14815172+liuwei-git@users.noreply.github.com> Date: Wed, 22 May 2024 04:28:32 +0800 Subject: llama : add phi3 128K model support (#7225) * add phi3 128k support in convert-hf-to-gguf * add phi3 128k support in cuda * address build warnings on llama.cpp * adjust index value in cuda long rope freq factors * add long rope support in ggml cpu backend * make freq factors only depend on ctx size * remove unused rope scaling type 'su' frin gguf converter * fix flint warnings on convert-hf-to-gguf.py * set to the short freq factor when context size is small than trained context size * add one line of comments * metal : support rope freq_factors * ggml : update ggml_rope_ext API to support freq. factors * backends : add dev messages to support rope freq. factors * minor : style * tests : update to use new rope API * backends : fix pragma semicolons * minor : cleanup * llama : move rope factors from KV header to tensors * llama : remove tmp assert * cuda : fix compile warning * convert : read/write n_head_kv * llama : fix uninitialized tensors --------- Co-authored-by: Georgi Gerganov --- examples/finetune/finetune.cpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'examples/finetune/finetune.cpp') diff --git a/examples/finetune/finetune.cpp b/examples/finetune/finetune.cpp index 22743b1b..992426c1 100644 --- a/examples/finetune/finetune.cpp +++ b/examples/finetune/finetune.cpp @@ -563,8 +563,8 @@ static struct ggml_tensor * llama_build_lora_finetune_graphs( // not capturing these, to silcence warnings const int rope_mode = 0; - return ggml_rope_custom(ctx, - t, KQ_pos, n_rot, rope_mode, n_ctx, 0, + return ggml_rope_ext(ctx, + t, KQ_pos, nullptr, n_rot, rope_mode, n_ctx, 0, rope_freq_base, rope_freq_scale, 0.0f, 1.0f, 0.0f, 0.0f ); }; -- cgit v1.2.3