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

llama : support all OpenELM models

Browse source 
* llama : add variable GQA and variable FFN sizes

Some metadata keys can now also be arrays to support setting
their value per-layer for models like OpenELM.
This commit is contained in:
Francis Couture-Harpin 2024-06-30 23:13:48 -04:00
parent 51b2577dd4
commit c8cdb48d10
5 changed files with 247 additions and 188 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -869,8 +869,9 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.ATTN_K_NORM,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.ARCTIC: [
MODEL_TENSOR.TOKEN_EMBD,

21
gguf-py/gguf/gguf_writer.py
View file

@ -480,8 +480,11 @@ class GGUFWriter:
def add_leading_dense_block_count(self, length: int) -> None:
self.add_uint32(Keys.LLM.LEADING_DENSE_BLOCK_COUNT.format(arch=self.arch), length)
def add_feed_forward_length(self, length: int) -> None:
self.add_uint32(Keys.LLM.FEED_FORWARD_LENGTH.format(arch=self.arch), length)
def add_feed_forward_length(self, length: int | Sequence[int]) -> None:
if isinstance(length, int):
self.add_uint32(Keys.LLM.FEED_FORWARD_LENGTH.format(arch=self.arch), length)
else:
self.add_array(Keys.LLM.FEED_FORWARD_LENGTH.format(arch=self.arch), length)
def add_expert_feed_forward_length(self, length: int) -> None:
self.add_uint32(Keys.LLM.EXPERT_FEED_FORWARD_LENGTH.format(arch=self.arch), length)
@ -495,11 +498,17 @@ class GGUFWriter:
def add_decoder_start_token_id(self, id: int) -> None:
self.add_uint32(Keys.LLM.DECODER_START_TOKEN_ID.format(arch=self.arch), id)
def add_head_count(self, count: int) -> None:
self.add_uint32(Keys.Attention.HEAD_COUNT.format(arch=self.arch), count)
def add_head_count(self, count: int | Sequence[int]) -> None:
if isinstance(count, int):
self.add_uint32(Keys.Attention.HEAD_COUNT.format(arch=self.arch), count)
else:
self.add_array(Keys.Attention.HEAD_COUNT.format(arch=self.arch), count)
def add_head_count_kv(self, count: int) -> None:
self.add_uint32(Keys.Attention.HEAD_COUNT_KV.format(arch=self.arch), count)
def add_head_count_kv(self, count: int | Sequence[int]) -> None:
if isinstance(count, int):
self.add_uint32(Keys.Attention.HEAD_COUNT_KV.format(arch=self.arch), count)
else:
self.add_array(Keys.Attention.HEAD_COUNT_KV.format(arch=self.arch), count)
def add_key_length(self, length: int) -> None:
self.add_uint32(Keys.Attention.KEY_LENGTH.format(arch=self.arch), length)

1
gguf-py/gguf/tensor_mapping.py
View file

@ -267,7 +267,6 @@ class TensorNameMap:
"encoder.layers.{bid}.mlp.fc11", # nomic-bert
"model.layers.{bid}.mlp.c_fc", # starcoder2
"encoder.layer.{bid}.mlp.gated_layers_v", # jina-bert-v2
"transformer.layers.{bid}.ffn.proj_1", # openelm
"model.layers.{bid}.residual_mlp.w3", # arctic
),