SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fixing quantization tests (#37650)

Browse Source 
* fix

* style

* add capability check
This commit is contained in:
Mohamed Mekkouri
2025-04-22 13:59:57 +02:00
committed by GitHub
parent b3492ff9f7
commit 38c406844e
4 changed files with 18 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/quantization/quanto_integration/test_quanto.py
View File

@@ -30,7 +30,7 @@ from transformers.utils import is_accelerate_available, is_optimum_quanto_availa
if is_torch_available():
import torch
from transformers import LlamaForCausalLM, LlamaTokenizer
from transformers import LlamaForCausalLM
if is_accelerate_available():
from accelerate import init_empty_weights
@@ -455,7 +455,7 @@ class QuantoKVCacheQuantizationTest(unittest.TestCase):
"Simply put, the theory of relativity states that ",
"My favorite all time favorite condiment is ketchup.",
]
tokenizer = LlamaTokenizer.from_pretrained(
tokenizer = AutoTokenizer.from_pretrained(
"unsloth/Llama-3.2-1B-Instruct", pad_token="</s>", padding_side="left"
)
model = LlamaForCausalLM.from_pretrained(