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

Merge branch 'ggerganov:master' into bitnet

Browse source
This commit is contained in:
Eddie-Wang 2024-06-10 10:51:47 +08:00 • committed by GitHub
commit 841c903ff9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
218 changed files with 5021 additions and 8134 deletions
Download patch file Download diff file Expand all files Collapse all files

3
gguf-py/gguf/tensor_mapping.py
View file

@ -102,6 +102,7 @@ class TensorNameMap:
# Attention norm 2
MODEL_TENSOR.ATTN_NORM_2: (
"transformer.h.{bid}.ln_attn", # falcon40b
"encoder.layer.{bid}.layer_norm_1", # jina-v2-code
),
# Attention query-key-value
@ -311,6 +312,7 @@ class TensorNameMap:
"model.layers.{bid}.mlp.c_proj", # starcoder2
"encoder.layer.{bid}.mlp.wo", # jina-bert-v2
"model.layers.{bid}.residual_mlp.w2", # arctic
"encoder.layer.{bid}.mlp.down_layer", # jina-bert-v2
),
MODEL_TENSOR.FFN_DOWN_EXP: (
@ -350,6 +352,7 @@ class TensorNameMap:
"encoder.layers.{bid}.norm2", # nomic-bert
"transformer.decoder_layer.{bid}.rms_norm_3", # Grok
"encoder.layer.{bid}.mlp.layernorm", # jina-bert-v2
"encoder.layer.{bid}.layer_norm_2" # jina-v2-code
),
MODEL_TENSOR.SSM_IN: (