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

llama : add support for Chameleon (#8543)

Browse source 
* convert chameleon hf to gguf

* add chameleon tokenizer tests

* fix lint

* implement chameleon graph

* add swin norm param

* return qk norm weights and biases to original format

* implement swin norm

* suppress image token output

* rem tabs

* add comment to conversion

* fix ci

* check for k norm separately

* adapt to new lora implementation

* fix layer input for swin norm

* move swin_norm in gguf writer

* add comment regarding special token regex in chameleon pre-tokenizer

* Update src/llama.cpp

Co-authored-by: compilade <git@compilade.net>

* fix punctuation regex in chameleon pre-tokenizer (@compilade)

Co-authored-by: compilade <git@compilade.net>

* fix lint

* trigger ci

---------

Co-authored-by: compilade <git@compilade.net>
This commit is contained in:
nopperl 2024-09-28 12:08:43 +00:00 • committed by GitHub
parent 43bcdd9703
commit 9a913110cf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 505 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -670,6 +670,9 @@ class GGUFWriter:
def add_expert_weights_scale(self, value: float) -> None:
self.add_float32(Keys.LLM.EXPERT_WEIGHTS_SCALE.format(arch=self.arch), value)
def add_swin_norm(self, value: bool) -> None:
self.add_bool(Keys.LLM.SWIN_NORM.format(arch=self.arch), value)
def add_rescale_every_n_layers(self, count: int) -> None:
self.add_uint32(Keys.LLM.RESCALE_EVERY_N_LAYERS.format(arch=self.arch), count)