mirror of
https://github.com/huggingface/trl.git
synced 2025-10-20 18:43:52 +08:00
453db5cd79
* first commit * uncomment * other tests adaptations * Remove unused variable in test_setup_chat_format * Remove unused import statement * style * Add Bart model * Update BCOTrainerTester class in test_bco_trainer.py * Update model IDs and tokenizers in test files * Add new models and processors * Update model IDs in test files * Fix formatting issue in test_dataset_formatting.py * Refactor dataset formatting in test_dataset_formatting.py * Fix dataset sequence length in SFTTrainerTester * Remove tokenizer * Remove print statement * Add reward_model_path and sft_model_path to PPO trainer * Fix tokenizer padding issue * Add chat template for testing purposes in PaliGemma model * Update PaliGemma model and chat template * Increase learning rate to speed up test * Update model names in run_dpo.sh and run_sft.sh scripts * Update model and dataset names * Fix formatting issue in test_dataset_formatting.py * Fix formatting issue in test_dataset_formatting.py * Remove unused chat template * Update model generation script * additional models * Update model references in test files * Remove unused imports in test_online_dpo_trainer.py * Add is_llm_blender_available import and update reward_tokenizer * Refactor test_online_dpo_trainer.py: Move skipped test case decorator * remove models without chat templates * Update model names in scripts and tests * Update model_id in test_modeling_value_head.py * Update model versions in test files * Fix formatting issue in test_dataset_formatting.py * Update embedding model ID in BCOTrainerTester * Update test_online_dpo_trainer.py with reward model changes * Update expected formatted text in test_dataset_formatting.py * Add reward_tokenizer to TestOnlineDPOTrainer * fix tests * Add SIMPLE_CHAT_TEMPLATE to T5 tokenizer * Fix dummy_text format in test_rloo_trainer.py * Skip outdated test for chatML data collator * Add new vision language models * Commented out unused model IDs in test_vdpo_trainer * Update model and vision configurations in generate_tiny_models.py and test_dpo_trainer.py * Update model and tokenizer references * Don't push if it already exists * Add comment explaining test skip * Fix model_exists function call and add new models * Update LlavaForConditionalGeneration model and processor * `qgallouedec` -> `trl-internal-testing`
67 lines
2.8 KiB
Python
67 lines
2.8 KiB
Python
# Copyright 2024 The HuggingFace Team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
import unittest
|
|
|
|
import torch
|
|
from transformers import AutoModelForCausalLM, GenerationConfig
|
|
|
|
from trl.models.modeling_base import GeometricMixtureWrapper, create_reference_model
|
|
|
|
|
|
class TestGeometricMixtureWrapper(unittest.TestCase):
|
|
def setUp(self):
|
|
model_id = "trl-internal-testing/tiny-Qwen2ForCausalLM-2.5"
|
|
self.model = AutoModelForCausalLM.from_pretrained(model_id)
|
|
self.ref_model = create_reference_model(self.model)
|
|
self.generation_config = GenerationConfig.from_pretrained(model_id)
|
|
self.mixture_coef = 0.5
|
|
self.wrapper = GeometricMixtureWrapper(
|
|
self.model, self.ref_model, self.generation_config, mixture_coef=self.mixture_coef
|
|
)
|
|
|
|
def test_forward(self):
|
|
input_ids = torch.tensor([[1, 2, 3, 4, 5]])
|
|
attention_mask = torch.ones_like(input_ids)
|
|
|
|
output = self.wrapper(input_ids=input_ids, attention_mask=attention_mask)
|
|
|
|
self.assertIsNotNone(output)
|
|
self.assertTrue(hasattr(output, "logits"))
|
|
self.assertEqual(output.logits.shape, (1, 5, self.model.config.vocab_size))
|
|
|
|
def test_mixture_coefficient(self):
|
|
input_ids = torch.tensor([[1, 2, 3, 4, 5]])
|
|
attention_mask = torch.ones_like(input_ids)
|
|
|
|
with torch.no_grad():
|
|
model_output = self.model(input_ids=input_ids, attention_mask=attention_mask)
|
|
ref_model_output = self.ref_model(input_ids=input_ids, attention_mask=attention_mask)
|
|
wrapper_output = self.wrapper(input_ids=input_ids, attention_mask=attention_mask)
|
|
|
|
expected_logits = torch.nn.functional.log_softmax(
|
|
self.mixture_coef * ref_model_output.logits + (1 - self.mixture_coef) * model_output.logits, dim=-1
|
|
)
|
|
|
|
self.assertTrue(torch.allclose(wrapper_output.logits, expected_logits, atol=1e-5))
|
|
|
|
def test_prepare_inputs_for_generation(self):
|
|
input_ids = torch.tensor([[1, 2, 3, 4, 5]])
|
|
attention_mask = torch.ones_like(input_ids)
|
|
|
|
inputs = self.wrapper.prepare_inputs_for_generation(input_ids, attention_mask=attention_mask, use_cache=True)
|
|
|
|
self.assertIn("input_ids", inputs)
|
|
self.assertIn("attention_mask", inputs)
|
|
self.assertFalse(inputs.get("use_cache", False))
|