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

llama : add OpenELM support (#7359)

Browse source 
* Initial OpenELM support (270M only so far)

* Fill out missing entries in llama_model_type_name

* fixup! Initial OpenELM support (270M only so far)

Fix formatting

* llama : support all OpenELM models

* 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.

* llama : minor spacing changes

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* llama : use std::array for per-layer hparams

* llama : fix save/load state

* llama : do not print hparams for vocab-only models

* llama : handle n_head == 0

* llama : use const ref for print_f and fix division by zero

* llama : fix t5 uses of n_head and n_ff

* llama : minor comment

---------

Co-authored-by: Francis Couture-Harpin <git@compilade.net>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Icecream95 2024-07-05 05:14:21 +12:00 • committed by GitHub
parent 6f63d646c1
commit d7fd29fff1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 676 additions and 176 deletions
Download patch file Download diff file Expand all files Collapse all files

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)