diff options
| author | Joan Fontanals <joan.fontanals.martinez@jina.ai> | 2024-06-06 09:22:41 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-06-06 10:22:41 +0300 |
| commit | f5d7b268ec4bf8628aa6ccc9f6631d0230dde76f (patch) | |
| tree | 2959e37f1baf783b97cd676e1e79a82cfad77c7f /gguf-py/gguf/tensor_mapping.py | |
| parent | 2d08b7fbb483c14bd2b173d4cd51ea3a4f862e8f (diff) | |
llama : add jina v2 base code (#7596)
* feat: add changes to handle jina v2 base code
* fix: do not complicate things
* fix: fix the usage of the code model
* fix: fix comments
* fix: fix linting issues
* fix: remove ollama patches
* style : minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'gguf-py/gguf/tensor_mapping.py')
| -rw-r--r-- | gguf-py/gguf/tensor_mapping.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index 83e3c4c3..81b4992a 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -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: ( |