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

Formatting

Browse source
This commit is contained in:
Ashish 2024-04-14 14:40:23 -07:00
parent 412a2807cb
commit 91728faac6
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
gguf-py/gguf/tensor_mapping.py
View file

@ -172,7 +172,7 @@ class TensorNameMap:
"encoder.layers.{bid}.attn.out_proj", # nomic-bert
"transformer.decoder_layer.{bid}.multi_head_attention.linear", # Grok
"transformer.blocks.{bid}.norm_attn_norm.attn.out_proj", # dbrx
),
),
# Attention output norm
MODEL_TENSOR.ATTN_OUT_NORM: (
@ -260,7 +260,7 @@ class TensorNameMap:
"layers.{bid}.feed_forward.experts.w1", # mixtral (merged)
"transformer.decoder_layer.{bid}.moe.linear", # Grok (merged)
"transformer.blocks.{bid}.ffn.experts.mlp.w1", # dbrx
),
),
# Feed-forward down
MODEL_TENSOR.FFN_DOWN: (