baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llm: consider head_dim in llama arch (#5817)

Browse source
This commit is contained in:
Jeffrey Morgan 2024-07-20 21:48:12 -04:00 committed by GitHub
parent d321297d8a
commit 5534f2cc6a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 19 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
llm/patches/11-embd_kv.diff Normal file
View file

@ -0,0 +1,19 @@
diff --git a/src/llama.cpp b/src/llama.cpp
index 2b9ace28..e60d3d8d 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -6052,10 +6052,10 @@ static bool llm_load_tensors(
layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
- layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd});
- layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa});
- layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa});
- layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
+ layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd_head_k * n_head});
+ layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_k_gqa});
+ layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_v_gqa});
+ layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head, n_embd});
// optional bias tensors
layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}, llama_model_loader::TENSOR_NOT_REQUIRED);