thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

ci : switch from pyright to ty (#20826)

Browse source 
* type fixes

* switch to ty

* tweak rules

* tweak more rules

* more tweaks

* final tweak

* use common import-not-found rule
This commit is contained in:
Sigbjørn Skjæret 2026-03-21 08:54:34 +01:00 • committed by GitHub
parent cea560f483
commit 29b28a9824
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 181 additions and 124 deletions
Download patch file Download diff file Expand all files Collapse all files

16
examples/model-conversion/scripts/embedding/run-original-model.py
View file

@ -64,7 +64,7 @@ def load_model_and_tokenizer(model_path, use_sentence_transformers=False, device
print("Using SentenceTransformer to apply all numbered layers")
model = SentenceTransformer(model_path)
tokenizer = model.tokenizer
config = model[0].auto_model.config # type: ignore
config = model[0].auto_model.config
else:
tokenizer = AutoTokenizer.from_pretrained(model_path)
config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
@ -108,8 +108,8 @@ def load_model_and_tokenizer(model_path, use_sentence_transformers=False, device
print(f"Model file: {type(model).__module__}")
# Verify the model is using the correct sliding window
if hasattr(model.config, 'sliding_window'): # type: ignore
print(f"Model's sliding_window: {model.config.sliding_window}") # type: ignore
if hasattr(model.config, 'sliding_window'):
print(f"Model's sliding_window: {model.config.sliding_window}")
else:
print("Model config does not have sliding_window attribute")
@ -152,7 +152,7 @@ def main():
device = next(model.parameters()).device
else:
# For SentenceTransformer, get device from the underlying model
device = next(model[0].auto_model.parameters()).device # type: ignore
device = next(model[0].auto_model.parameters()).device
model_name = os.path.basename(model_path)
@ -177,7 +177,7 @@ def main():
print(f"{token_id:6d} -> '{token_str}'")
print(f"Embeddings shape (after all SentenceTransformer layers): {all_embeddings.shape}")
print(f"Embedding dimension: {all_embeddings.shape[1] if len(all_embeddings.shape) > 1 else all_embeddings.shape[0]}") # type: ignore
print(f"Embedding dimension: {all_embeddings.shape[1] if len(all_embeddings.shape) > 1 else all_embeddings.shape[0]}")
else:
# Standard approach: use base model output only
encoded = tokenizer(
@ -205,12 +205,12 @@ def main():
print(f"Embedding dimension: {all_embeddings.shape[1]}")
if len(all_embeddings.shape) == 1:
n_embd = all_embeddings.shape[0] # type: ignore
n_embd = all_embeddings.shape[0]
n_embd_count = 1
all_embeddings = all_embeddings.reshape(1, -1)
else:
n_embd = all_embeddings.shape[1] # type: ignore
n_embd_count = all_embeddings.shape[0] # type: ignore
n_embd = all_embeddings.shape[1]
n_embd_count = all_embeddings.shape[0]
print()