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

4
gguf-py/gguf/tensor_mapping.py
View file

@ -380,7 +380,7 @@ class TensorNameMap:
MODEL_TENSOR.ATTN_Q_NORM: (
"language_model.encoder.layers.{bid}.self_attention.q_layernorm",
"model.layers.{bid}.self_attn.q_layernorm", # persimmon
"model.layers.{bid}.self_attn.q_norm", # cohere olmoe
"model.layers.{bid}.self_attn.q_norm", # cohere olmoe chameleon
"transformer.blocks.{bid}.attn.q_ln", # sea-lion
"encoder.layer.{bid}.attention.self.layer_norm_q", # jina-bert-v2
"transformer.layers.{bid}.attn.q_norm", # openelm
@ -389,7 +389,7 @@ class TensorNameMap:
MODEL_TENSOR.ATTN_K_NORM: (
"language_model.encoder.layers.{bid}.self_attention.k_layernorm",
"model.layers.{bid}.self_attn.k_layernorm", # persimmon
"model.layers.{bid}.self_attn.k_norm", # cohere olmoe
"model.layers.{bid}.self_attn.k_norm", # cohere olmoe chameleon
"transformer.blocks.{bid}.attn.k_ln", # sea-lion
"encoder.layer.{bid}.attention.self.layer_norm_k", # jina-bert-v2
"transformer.layers.{bid}.attn.k_norm", # openelm