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

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
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
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,

10
gguf-py/gguf/tensor_mapping.py
View file

@ -17,6 +17,7 @@ class TensorNameMap:
"tok_embeddings", # llama-pth
"embeddings.word_embeddings", # bert
"language_model.embedding.word_embeddings", # persimmon
"wte", # gpt2
"transformer.embd.wte", # phi2
),
@ -34,6 +35,7 @@ class TensorNameMap:
MODEL_TENSOR.POS_EMBD: (
"transformer.wpe", # gpt2
"embeddings.position_embeddings", # bert
"wpe", # gpt2
),
# Output
@ -53,7 +55,7 @@ class TensorNameMap:
"norm", # llama-pth
"embeddings.LayerNorm", # bert
"transformer.norm_f", # mpt
"ln_f", # refact bloom qwen
"ln_f", # refact bloom qwen gpt2
"language_model.encoder.final_layernorm", # persimmon
"lm_head.ln", # phi2
),
@ -78,6 +80,7 @@ class TensorNameMap:
"encoder.layer.{bid}.attention.output.LayerNorm", # bert
"language_model.encoder.layers.{bid}.input_layernorm", # persimmon
"model.layers.{bid}.ln1", # yi
"h.{bid}.ln_1", # gpt2
"transformer.h.{bid}.ln", # phi2
"model.layers.layers.{bid}.norm", # plamo
),
@ -95,6 +98,7 @@ class TensorNameMap:
"transformer.h.{bid}.self_attention.query_key_value", # falcon
"h.{bid}.self_attention.query_key_value", # bloom
"language_model.encoder.layers.{bid}.self_attention.query_key_value", # persimmon
"h.{bid}.attn.c_attn", # gpt2
"transformer.h.{bid}.mixer.Wqkv", # phi2
),
@ -137,6 +141,7 @@ class TensorNameMap:
"encoder.layer.{bid}.attention.output.dense", # bert
"transformer.h.{bid}.attn.out_proj", # gpt-j
"language_model.encoder.layers.{bid}.self_attention.dense", # persimmon
"h.{bid}.attn.c_proj", # gpt2
"transformer.h.{bid}.mixer.out_proj", # phi2
"model.layers.layers.{bid}.self_attn.o_proj", # plamo
),
@ -159,6 +164,7 @@ class TensorNameMap:
"encoder.layer.{bid}.output.LayerNorm", # bert
"language_model.encoder.layers.{bid}.post_attention_layernorm", # persimmon
"model.layers.{bid}.ln2", # yi
"h.{bid}.ln_2", # gpt2
),
MODEL_TENSOR.FFN_GATE_INP: (
@ -179,6 +185,7 @@ class TensorNameMap:
"transformer.h.{bid}.mlp.fc_in", # gpt-j
"language_model.encoder.layers.{bid}.mlp.dense_h_to_4h", # persimmon
"transformer.h.{bid}.mlp.w1", # qwen
"h.{bid}.mlp.c_fc", # gpt2
"transformer.h.{bid}.mlp.fc1", # phi2
"model.layers.layers.{bid}.mlp.up_proj", # plamo
),
@ -218,6 +225,7 @@ class TensorNameMap:
"encoder.layer.{bid}.output.dense", # bert
"transformer.h.{bid}.mlp.fc_out", # gpt-j
"language_model.encoder.layers.{bid}.mlp.dense_4h_to_h", # persimmon
"h.{bid}.mlp.c_proj", # gpt2
"transformer.h.{bid}.mlp.fc2", # phi2
"model.layers.layers.{bid}.mlp.down_proj", # plamo
),