CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

gpt2 : Add gpt2 architecture integration (#4555)

Browse Source
This commit is contained in:
manikbhandari
2023-12-28 09:03:57 -05:00
committed by GitHub
parent f6793491b5
commit ea5497df5d
7 changed files with 281 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
gguf-py/gguf/constants.py
View File

@@ -370,7 +370,16 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.GPT2: [
# TODO
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.POS_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.PHI2: [
MODEL_TENSOR.TOKEN_EMBD,