py : add Gemma conversion from HF models (#5647)

* py : add gemma conversion from HF models

* Update convert-hf-to-gguf.py

Co-authored-by: Aarni Koskela <akx@iki.fi>

* Update convert-hf-to-gguf.py

Co-authored-by: Aarni Koskela <akx@iki.fi>

* Update convert-hf-to-gguf.py

Co-authored-by: Jared Van Bortel <jared@nomic.ai>

---------

Co-authored-by: Aarni Koskela <akx@iki.fi>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>

1 files changed, 3 insertions, 0 deletions

diff --git a/llama.cpp b/llama.cpp
index 40dda265..7770fa0e 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -7450,6 +7450,7 @@ struct llm_build_context {
 
         inpL = llm_build_inp_embd(ctx0, hparams, batch, model.tok_embd, lctx.inp_tokens, lctx.inp_embd, cb);
         cb(inpL, "inp_embd", -1);
+
         inpL = ggml_scale(ctx0, inpL, sqrtf(n_embd));
         cb(inpL, "inp_scaled", -1);
 
@@ -7491,6 +7492,7 @@ struct llm_build_context {
                         n_embd_head_k, 2, 0, n_orig_ctx, freq_base, freq_scale,
                         ext_factor, attn_factor, beta_fast, beta_slow);
                 cb(Qcur, "Qcur", il);
+
                 Qcur = ggml_scale(ctx0, Qcur, 1.0f / sqrtf(float(n_embd_head_k)));
                 cb(Qcur, "Qcur_scaled", il);
 
@@ -7505,6 +7507,7 @@ struct llm_build_context {
                         Kcur, Vcur, Qcur, KQ_mask, nullptr, n_ctx, n_tokens, kv_head, n_kv, 1.0f, cb, il);
                 cb(cur, "kqv_out", il);
             }
+
             struct ggml_tensor * sa_out = ggml_add(ctx0, cur, inpL);
             cb(sa_out, "sa_out", il);