CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix qs.n_attention_wv for DeepSeek-V2 (#9156)

Browse Source
This commit is contained in:
compilade
2024-08-27 06:09:23 -04:00
committed by GitHub
parent a77feb5d71
commit 78eb487bb0
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama.cpp
View File

@@ -16822,7 +16822,8 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
// 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) {
name.find("attn_qkv.weight") != std::string::npos ||
name.find("attn_kv_b.weight")!= std::string::npos) {
++qs.n_attention_wv;
} else if (name == LLM_TN(model.arch)(LLM_TENSOR_OUTPUT, "weight")) {
qs.has_output = true;