Skip to content

Commit

Permalink
Update llama_rope_type.
Browse files Browse the repository at this point in the history
  • Loading branch information
dranger003 committed Dec 19, 2024
1 parent 5e2dcb4 commit d92e1ad
Showing 1 changed file with 5 additions and 5 deletions.
10 changes: 5 additions & 5 deletions src/llama.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -14891,13 +14891,13 @@ struct llm_build_context {
}

Qcur = ggml_rope_ext(ctx0, ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens), inp_pos, nullptr,
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, ext_factor, attn_factor,
beta_fast, beta_slow);
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, ext_factor, attn_factor,
beta_fast, beta_slow);
cb(Qcur, "Qcur", il);

Kcur = ggml_rope_ext(ctx0, ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens), inp_pos,
nullptr, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, ext_factor,
attn_factor, beta_fast, beta_slow);
nullptr, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, ext_factor,
attn_factor, beta_fast, beta_slow);
cb(Kcur, "Kcur", il);

cur = llm_build_kv(ctx0, lctx, kv_self, gf, model.layers[il].wo, model.layers[il].bo, Kcur, Vcur, Qcur,
Expand Down Expand Up @@ -20974,6 +20974,7 @@ enum llama_rope_type llama_rope_type(const struct llama_model * model) {
case LLM_ARCH_MINICPM:
case LLM_ARCH_XVERSE:
case LLM_ARCH_COMMAND_R:
case LLM_ARCH_COHERE2:
case LLM_ARCH_OLMO:
case LLM_ARCH_ARCTIC:
case LLM_ARCH_DEEPSEEK:
Expand Down Expand Up @@ -21008,7 +21009,6 @@ enum llama_rope_type llama_rope_type(const struct llama_model * model) {
case LLM_ARCH_NEMOTRON:
case LLM_ARCH_EXAONE:
case LLM_ARCH_MINICPM3:
case LLM_ARCH_COHERE2:
return LLAMA_ROPE_TYPE_NEOX;

case LLM_ARCH_QWEN2VL:
Expand Down

0 comments on commit d92e1ad

Please sign in to comment.