haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

llama : fix Baichuan2 13B (#6092)

Browse source
This commit is contained in:
slaren 2024-03-15 22:14:16 +01:00 committed by GitHub
parent 877b4d0c62
commit d84c48505f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
llama.cpp
View file

@ -6000,7 +6000,7 @@ struct llm_build_context {
inpL = llm_build_inp_embd(ctx0, lctx, hparams, batch, model.tok_embd, cb);
// inp_pos - contains the positions
struct ggml_tensor * inp_pos = build_inp_pos();
struct ggml_tensor * inp_pos = model.type == MODEL_7B ? build_inp_pos() : nullptr;
// KQ_mask (mask for 1 head, it will be broadcasted to all heads)
struct ggml_tensor * KQ_mask = build_inp_KQ_mask();
@ -6050,7 +6050,6 @@ struct llm_build_context {
cb(Qcur, "Qcur", il);
cb(Kcur, "Kcur", il);
cur = llm_build_kv(ctx0, model, hparams, kv_self, gf,
model.layers[il].wo, NULL,
Kcur, Vcur, Qcur, KQ_mask, KQ_pos, n_ctx, n_tokens, kv_head, n_kv, 1.0f/sqrtf(float(n_embd_head)), cb, il);