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

Fix slow tests for important models to be compatible with A10 runners (#29905)

Browse Source 
* fix mistral and mixtral

* add pdb

* fix mixtral tesst

* fix

* fix mistral ?

* add fix gemma

* fix mistral

* fix

* test

* anoter test

* fix

* fix

* fix mistral tests

* fix them again

* final fixes for mistral

* fix padding right

* fix whipser fa2

* fix

* fix

* fix gemma

* test

* fix llama

* fix

* fix

* fix llama gemma

* add class attribute

* fix CI

* clarify whisper

* compute_capability

* rename names in some comments

* Add   # fmt: skip

* make style

* Update tests/models/mistral/test_modeling_mistral.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* update

* update

---------

Co-authored-by: Younes Belkada <younesbelkada@gmail.com>
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
This commit is contained in:
Yih-Dar
2024-04-09 13:28:54 +02:00
committed by GitHub
parent e9c23fa056
commit 08a194fcd6
6 changed files with 246 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
tests/models/llama/test_modeling_llama.py
View File

@@ -597,8 +597,18 @@ class LlamaModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixi
pass
@require_torch
@require_torch_gpu
class LlamaIntegrationTest(unittest.TestCase):
# This variable is used to determine which CUDA device are we using for our runners (A10 or T4)
# Depending on the hardware we get different logits / generations
cuda_compute_capability_major_version = None
@classmethod
def setUpClass(cls):
if is_torch_available() and torch.cuda.is_available():
# 8 is for A100 / A10 and 7 for T4
cls.cuda_compute_capability_major_version = torch.cuda.get_device_capability()[0]
@unittest.skip("Logits are not exactly the same, once we fix the instabalities somehow, will update!")
@slow
def test_model_7b_logits(self):
@@ -675,16 +685,25 @@ class LlamaIntegrationTest(unittest.TestCase):
@require_read_token
def test_compile_static_cache(self):
NUM_TOKENS_TO_GENERATE = 40
EXPECTED_TEXT_COMPLETION = [
"Simply put, the theory of relativity states that 1) the speed of light is constant, 2) the speed of light is the same for all observers, and 3) the laws of physics are the same for all observers.",
"My favorite all time favorite condiment is ketchup. I love it on everything. I love it on my eggs, my fries, my chicken, my burgers, my hot dogs, my sandwiches, my salads, my p",
]
EXPECTED_TEXT_COMPLETION = {
7: [
"Simply put, the theory of relativity states that 1) the speed of light is constant, 2) the speed of light is the same for all observers, and 3) the laws of physics are the same for all observers.",
"My favorite all time favorite condiment is ketchup. I love it on everything. I love it on my eggs, my fries, my chicken, my burgers, my hot dogs, my sandwiches, my salads, my p",
],
8: [
"Simply put, the theory of relativity states that 1) the speed of light is the same for all observers, and 2) the laws of physics are the same for all observers.\nThe first part of the theory of relativity",
"My favorite all time favorite condiment is ketchup. I love it on everything. I love it on my eggs, my fries, my chicken, my burgers, my hot dogs, my sandwiches, my salads, my p",
],
}
prompts = [
"Simply put, the theory of relativity states that ",
"My favorite all time favorite condiment is ketchup.",
]
tokenizer = LlamaTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf", pad_token="</s>", padding_side="right")
model = LlamaForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf", device_map="sequential")
model = LlamaForCausalLM.from_pretrained(
"meta-llama/Llama-2-7b-hf", device_map="sequential", torch_dtype=torch.float16
)
inputs = tokenizer(prompts, return_tensors="pt", padding=True).to(model.device)
def decode_one_tokens(model, cur_token, input_pos, cache_position):
@@ -718,7 +737,7 @@ class LlamaIntegrationTest(unittest.TestCase):
cache_position += 1
text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
self.assertEqual(EXPECTED_TEXT_COMPLETION, text)
self.assertEqual(EXPECTED_TEXT_COMPLETION[self.cuda_compute_capability_major_version], text)
@require_torch
@@ -763,6 +782,7 @@ end
@require_torch_accelerator
@slow
@unittest.skip("Model is too large")
def test_model_7b_logits(self):
model = LlamaForCausalLM.from_pretrained("codellama/CodeLlama-7b-hf").to(torch_device)
tokenizer = CodeLlamaTokenizer.from_pretrained("codellama/CodeLlama-7b-hf")