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

py : type-check all Python scripts with Pyright (#8341)

Browse source 
* py : type-check all Python scripts with Pyright

* server-tests : use trailing slash in openai base_url

* server-tests : add more type annotations

* server-tests : strip "chat" from base_url in oai_chat_completions

* server-tests : model metadata is a dict

* ci : disable pip cache in type-check workflow

The cache is not shared between branches, and it's 250MB in size,
so it would become quite a big part of the 10GB cache limit of the repo.

* py : fix new type errors from master branch

* tests : fix test-tokenizer-random.py

Apparently, gcc applies optimisations even when pre-processing,
which confuses pycparser.

* ci : only show warnings and errors in python type-check

The "information" level otherwise has entries
from 'examples/pydantic_models_to_grammar.py',
which could be confusing for someone trying to figure out what failed,
considering that these messages can safely be ignored
even though they look like errors.
This commit is contained in:
compilade 2024-07-07 15:04:39 -04:00 • committed by GitHub
parent a8db2a9ce6
commit 3fd62a6b1c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 297 additions and 173 deletions
Download patch file Download diff file Expand all files Collapse all files

10
examples/llava/convert_image_encoder_to_gguf.py
View file

@ -185,6 +185,8 @@ else:
fout.add_description("two-tower CLIP model")
if has_text_encoder:
assert t_hparams is not None
assert tokens is not None
# text_model hparams
fout.add_uint32(k(KEY_CONTEXT_LENGTH, TEXT), t_hparams["max_position_embeddings"])
fout.add_uint32(k(KEY_EMBEDDING_LENGTH, TEXT), t_hparams["hidden_size"])
@ -259,8 +261,8 @@ if has_vision_encoder:
if processor is not None:
image_mean = processor.image_processor.image_mean if args.image_mean is None or args.image_mean == default_image_mean else args.image_mean
image_std = processor.image_processor.image_std if args.image_std is None or args.image_std == default_image_std else args.image_std
image_mean = processor.image_processor.image_mean if args.image_mean is None or args.image_mean == default_image_mean else args.image_mean # pyright: ignore[reportAttributeAccessIssue]
image_std = processor.image_processor.image_std if args.image_std is None or args.image_std == default_image_std else args.image_std # pyright: ignore[reportAttributeAccessIssue]
else:
image_mean = args.image_mean if args.image_mean is not None else default_image_mean
image_std = args.image_std if args.image_std is not None else default_image_std
@ -272,7 +274,7 @@ fout.add_bool("clip.use_gelu", use_gelu)
if has_llava_projector:
model.vision_model.encoder.layers.pop(-1)
model.vision_model.encoder.layers.pop(-1) # pyright: ignore[reportAttributeAccessIssue]
projector = torch.load(args.llava_projector)
for name, data in projector.items():
name = get_tensor_name(name)
@ -286,7 +288,7 @@ if has_llava_projector:
print("Projector tensors added\n")
state_dict = model.state_dict()
state_dict = model.state_dict() # pyright: ignore[reportAttributeAccessIssue]
for name, data in state_dict.items():
if should_skip_tensor(name, has_text_encoder, has_vision_encoder, has_llava_projector):
# we don't need this