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 non-quantization of expert gating tensors (#5754)

Browse Source 
This reverts a single line from #5475
This commit is contained in:
compilade
2024-02-28 03:52:56 -05:00
committed by GitHub
parent 177628bfd8
commit adcb12a9ba
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
llama.cpp
View File

@@ -11162,7 +11162,8 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
quantize &= !params->only_copy;
// do not quantize expert gating tensors
quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_FFN_GATE_INP, "weight");
// NOTE: can't use LLM_TN here because the layer number is not known
quantize &= name.find("ffn_gate_inp.weight") == std::string::npos;
// do not quantize positional embeddings and token types (BERT)
quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_POS_EMBD, "weight");