root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-09-22 21:16:20 +00:00
Code Issues Actions 16 Packages Projects Releases Wiki Activity

llama : fix attention layer count sanity check (#6550)

Browse Source 
* llama : fix attention layer count sanity check

* llama : fix parentheses in attention layer count sanity check

There was otherwise a warning when compiling.

---------

Co-authored-by: Francis Couture-Harpin <git@compilade.net>
This commit is contained in:
Georgi Gerganov 2024-04-08 22:25:49 +03:00 committed by GitHub
parent cecd8d3c98
commit cc4a95426d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llama.cpp
View File

@ -13468,7 +13468,8 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
const std::string name = ggml_get_name(meta);
// TODO: avoid hardcoded tensor names - use the TN_* constants
if (name.find("attn_v.weight") != std::string::npos || name.find("attn_qkv.weight") != std::string::npos) {
if (name.find("attn_v.weight") != std::string::npos ||
name.find("attn_qkv.weight") != std::string::npos) {
++qs.n_attention_wv;
} else if (name == LLM_TN(model.arch)(LLM_TENSOR_OUTPUT, "weight")) {
qs.has_output = true;
@ -13478,7 +13479,11 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)model.hparams.n_layer;
// sanity checks
GGML_ASSERT(qs.n_attention_wv == (int)model.hparams.n_layer && "n_attention_wv != n_layer is unexpected");
//
// - qs.n_attention_wv == 0 for Mamba models
// - qs.n_attention_wv == model.hparams.n_layer for Transformer models
//
GGML_ASSERT((qs.n_attention_wv == 0 || qs.n_attention_wv == (int)model.hparams.n_layer) && "n_attention_wv is unexpected");
size_t total_size_org = 0;
size_t total_size_new = 0;