riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-24 23:08:57 +06:00
Code Issues Actions 32 Packages Projects Releases Wiki Activity

Fix FalconMambaIntegrationTests (#38566)

Browse Source 
* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Yih-Dar 2025-06-19 13:50:33 +02:00 committed by GitHub
parent a9ce8c69c9
commit 5d26a38735
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 52 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

64
tests/models/falcon_mamba/test_modeling_falcon_mamba.py
View File

@ -19,9 +19,12 @@ from unittest.util import safe_repr
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, FalconMambaConfig, is_torch_available from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, FalconMambaConfig, is_torch_available
from transformers.testing_utils import ( from transformers.testing_utils import (
Expectations,
cleanup,
require_bitsandbytes, require_bitsandbytes,
require_torch, require_torch,
require_torch_accelerator, require_torch_accelerator,
require_torch_large_accelerator,
require_torch_multi_accelerator, require_torch_multi_accelerator,
require_torch_multi_gpu, require_torch_multi_gpu,
slow, slow,
@ -450,15 +453,30 @@ class FalconMambaIntegrationTests(unittest.TestCase):
self.tokenizer = AutoTokenizer.from_pretrained(self.model_id) self.tokenizer = AutoTokenizer.from_pretrained(self.model_id)
self.text = "Hello today" self.text = "Hello today"
def test_generation_bf16(self): cleanup(torch_device, gc_collect=True)
model = AutoModelForCausalLM.from_pretrained(self.model_id, torch_dtype=torch.bfloat16, device_map="auto")
def tearDown(self):
cleanup(torch_device, gc_collect=True)
# On T4, get `NotImplementedError: Cannot copy out of meta tensor; no data!`
@require_torch_large_accelerator
def test_generation_fp16(self):
model = AutoModelForCausalLM.from_pretrained(self.model_id, torch_dtype=torch.float16, device_map="auto")
inputs = self.tokenizer(self.text, return_tensors="pt").to(torch_device) inputs = self.tokenizer(self.text, return_tensors="pt").to(torch_device)
out = model.generate(**inputs, max_new_tokens=20, do_sample=False) out = model.generate(**inputs, max_new_tokens=20, do_sample=False)
EXPECTED_OUTPUTS = Expectations(
{
("cuda", 7): "Hello today I am going to show you how to make a simple and easy to make paper plane.\nStep",
("cuda", 8): 'Hello today Iava,\n\nI am writing to you today to discuss the importance of maintaining a healthy lifestyle',
}
) # fmt: skip
EXPECTED_OUTPUT = EXPECTED_OUTPUTS.get_expectation()
self.assertEqual( self.assertEqual(
self.tokenizer.batch_decode(out, skip_special_tokens=False)[0], self.tokenizer.batch_decode(out, skip_special_tokens=False)[0],
"Hello today I am going to show you how to make a simple and easy to make paper plane.\nStep", EXPECTED_OUTPUT,
) )
@require_bitsandbytes @require_bitsandbytes
@ -471,11 +489,11 @@ class FalconMambaIntegrationTests(unittest.TestCase):
self.assertEqual( self.assertEqual(
self.tokenizer.batch_decode(out, skip_special_tokens=False)[0], self.tokenizer.batch_decode(out, skip_special_tokens=False)[0],
"""Hello today I'm going to talk about the "C" in the "C-I-""", "Hello today Iava,\n\nI'm sorry to hear that you're having trouble with the ",
) )
def test_generation_torch_compile(self): def test_generation_torch_compile(self):
model = AutoModelForCausalLM.from_pretrained(self.model_id, torch_dtype=torch.bfloat16).to(torch_device) model = AutoModelForCausalLM.from_pretrained(self.model_id, torch_dtype=torch.float16).to(torch_device)
model = torch.compile(model) model = torch.compile(model)
inputs = self.tokenizer(self.text, return_tensors="pt").to(torch_device) inputs = self.tokenizer(self.text, return_tensors="pt").to(torch_device)
@ -483,7 +501,7 @@ class FalconMambaIntegrationTests(unittest.TestCase):
self.assertEqual( self.assertEqual(
self.tokenizer.batch_decode(out, skip_special_tokens=False)[0], self.tokenizer.batch_decode(out, skip_special_tokens=False)[0],
"Hello today I am going to show you how to make a simple and easy to make paper plane.\nStep", "Hello today Iava,\n\nI am writing to you today to discuss the importance of maintaining a healthy lifestyle",
) )
def test_batched_generation(self): def test_batched_generation(self):
@ -493,13 +511,22 @@ class FalconMambaIntegrationTests(unittest.TestCase):
texts = ["Hello today", "Hello my name is Younes and today"] texts = ["Hello today", "Hello my name is Younes and today"]
EXPECTED_OUTPUT = [ EXPECTED_OUTPUTS = Expectations(
"Hello today I'm going to show you how to make a 3D model of a house.\n", {
"Hello my name is Younes and today I will be talking about the topic of “The importance of the internet in our life”.\n", ("cuda", 7): [
] 'Hello today I will be talking about the “Theory of Relativity” by Albert Einstein.\nThe',
'Hello my name is Younes and today I will be talking about the importance of the internet in our lives.\nThe internet is a global',
],
("cuda", 8): [
'Hello today I am going to talk about the “Theory of Relativity” by Albert Einstein.\n',
'Hello my name is Younes and today I will be talking about the importance of the internet in our lives.\nThe internet is a global',
],
}
) # fmt: skip
EXPECTED_OUTPUT = EXPECTED_OUTPUTS.get_expectation()
inputs = tok(texts, return_tensors="pt", padding=True, return_token_type_ids=False).to(torch_device) inputs = tok(texts, return_tensors="pt", padding=True, return_token_type_ids=False).to(torch_device)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map=0, torch_dtype=torch.bfloat16) model = AutoModelForCausalLM.from_pretrained(model_id, device_map=0, torch_dtype=torch.float16)
out = model.generate(**inputs, max_new_tokens=20) out = model.generate(**inputs, max_new_tokens=20)
out = tok.batch_decode(out, skip_special_tokens=True) out = tok.batch_decode(out, skip_special_tokens=True)
@ -514,6 +541,19 @@ class FalconMambaIntegrationTests(unittest.TestCase):
out = model.generate(**inputs, max_new_tokens=20) out = model.generate(**inputs, max_new_tokens=20)
out = tok.batch_decode(out, skip_special_tokens=True) out = tok.batch_decode(out, skip_special_tokens=True)
EXPECTED_OUTPUTS = Expectations(
{
("cuda", 7): [
' I will be talking about the “Theory of Relativity” by Albert Einstein.\nThe',
' I will be talking about the importance of the internet in our lives.\nThe internet is a global',
],
("cuda", 8): [
' I am going to talk about the “Theory of Relativity” by Albert Einstein.\n',
' I will be talking about the importance of the internet in our lives.\nThe internet is a global'
],
}
) # fmt: skip
EXPECTED_OUTPUT = EXPECTED_OUTPUTS.get_expectation()
self.assertListEqual(out, EXPECTED_OUTPUT) self.assertListEqual(out, EXPECTED_OUTPUT)
@require_torch_multi_accelerator @require_torch_multi_accelerator
@ -521,7 +561,7 @@ class FalconMambaIntegrationTests(unittest.TestCase):
model_id = "tiiuae/falcon-mamba-7b" model_id = "tiiuae/falcon-mamba-7b"
tokenizer = AutoTokenizer.from_pretrained(model_id) tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16) model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
tokenizer.pad_token_id = tokenizer.eos_token_id tokenizer.pad_token_id = tokenizer.eos_token_id
text = "Hello today" text = "Hello today"