[Oneshot Refactor] Main refactor (#1110)

ORDER OF REVIEWS:
1. #1108
2. #1103 
3. #1109
4. #1110 <- current
PR


SUMMARY:
* Create a class to decouple dependency to `main`. Class `Oneshot`
consists of pre-processing, carrying out oneshot logic and
post-processing
* Move the oneshot class and method under
`llmcompressor/entrypoints/oneshot.py`.
* Add ReadMe in `/llmcompressor/entrypoints` for info on oneshot
* Delete oneshot logic from `/finetune` directory, add deprecation
warning
* Remove apply used only for stagerunner oneshot pathway in session.py
and session_function.py
* Add oneshot only calibration dataloader logic
* Add a return variable of `model: PretrainedModel` for `def oneshot`.
* Make oneshot carryout logic independent of `TrainingArguments`
* remove `overwrite_output_dir` as oneshot input arg -> only used for
`TrainingArguments`
* Update README on `/finetune` path. Remove `oneshot` logic and `oneshot
with fsdp`
* Update `wrap_save_pretrained` logic to run only if not updated already
-> used for stage runner to avoid double wrapping



Entrypoints: 
```python3
from llmcompressor import oneshot
oneshot(**kwargs) # calls Oneshot
```

or 

```python3
from llmcompressor import Oneshot
oneshot = Oneshot(**kwargs)
oneshot() # preprocesss, carries out logic and post process
```


TEST PLAN:
Pass all tests and examples. 
Verified
https://github.com/vllm-project/llm-compressor/blob/main/examples/quantization_2of4_sparse_w4a16/llama7b_sparse_w4a16.py
works as expected.

FOLLOW UPS:
* Stage runner removal
* Update entrypoints folder with train, eval, predict, etc.

---------

Signed-off-by: George Ohashi <george@neuralmagic.com>
Signed-off-by: George <george@neuralmagic.com>

Author: George

README.md

@@ -58,7 +58,7 @@ Quantization is applied by selecting an algorithm and calling the `oneshot` API.
 ```python
 from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
 from llmcompressor.modifiers.quantization import GPTQModifier
-from llmcompressor.transformers import oneshot
+from llmcompressor import oneshot
 
 # Select quantization algorithm. In this case, we:
 #   * apply SmoothQuant to make the activations easier to quantize

examples/big_models_with_accelerate/cpu_offloading_fp8.py

@@ -1,7 +1,7 @@
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
+from llmcompressor import oneshot
 from llmcompressor.modifiers.quantization import QuantizationModifier
-from llmcompressor.transformers import oneshot
 
 MODEL_ID = "meta-llama/Meta-Llama-3-70B-Instruct"
 OUTPUT_DIR = MODEL_ID.split("/")[1] + "-FP8-Dynamic"

examples/big_models_with_accelerate/mult_gpus_int8_device_map.py

@@ -2,9 +2,9 @@
 from datasets import load_dataset
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
+from llmcompressor import oneshot
 from llmcompressor.modifiers.quantization import GPTQModifier
 from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
-from llmcompressor.transformers import oneshot
 from llmcompressor.transformers.compression.helpers import calculate_offload_device_map
 
 MODEL_ID = "meta-llama/Meta-Llama-3-70B-Instruct"

examples/big_models_with_accelerate/multi_gpu_int8.py

@@ -1,8 +1,8 @@
 from datasets import load_dataset
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
+from llmcompressor import oneshot
 from llmcompressor.modifiers.quantization import GPTQModifier
-from llmcompressor.transformers import oneshot
 
 MODEL_ID = "meta-llama/Meta-Llama-3-70B-Instruct"
 SAVE_DIR = MODEL_ID.split("/")[1] + "-W8A8-Dynamic"

examples/multimodal_audio/whisper_example.py

@@ -2,8 +2,8 @@
 from datasets import load_dataset
 from transformers import WhisperProcessor
 
+from llmcompressor import oneshot
 from llmcompressor.modifiers.quantization import GPTQModifier
-from llmcompressor.transformers import oneshot
 from llmcompressor.transformers.tracing import TraceableWhisperForConditionalGeneration
 
 # Select model and load it.

examples/multimodal_vision/idefics3_example.py

@@ -4,8 +4,8 @@
 from PIL import Image
 from transformers import AutoProcessor
 
+from llmcompressor import oneshot
 from llmcompressor.modifiers.quantization import GPTQModifier
-from llmcompressor.transformers import oneshot
 from llmcompressor.transformers.tracing import TraceableIdefics3ForConditionalGeneration
 
 # Load model.

examples/multimodal_vision/llava_example.py

@@ -3,8 +3,8 @@
 from PIL import Image
 from transformers import AutoProcessor
 
+from llmcompressor import oneshot
 from llmcompressor.modifiers.quantization import GPTQModifier
-from llmcompressor.transformers import oneshot
 from llmcompressor.transformers.tracing import TraceableLlavaForConditionalGeneration
 
 # Load model.

examples/multimodal_vision/mllama_example.py

@@ -3,8 +3,8 @@
 from PIL import Image
 from transformers import AutoProcessor
 
+from llmcompressor import oneshot
 from llmcompressor.modifiers.quantization import GPTQModifier
-from llmcompressor.transformers import oneshot
 from llmcompressor.transformers.tracing import TraceableMllamaForConditionalGeneration
 
 # Load model.

examples/multimodal_vision/phi3_vision_example.py

@@ -5,8 +5,8 @@
 from datasets import load_dataset
 from transformers import AutoModelForCausalLM, AutoProcessor
 
+from llmcompressor import oneshot
 from llmcompressor.modifiers.quantization import GPTQModifier
-from llmcompressor.transformers import oneshot
 
 # Load model.
 model_id = "microsoft/Phi-3-vision-128k-instruct"

examples/multimodal_vision/pixtral_example.py

@@ -3,8 +3,8 @@
 from PIL import Image
 from transformers import AutoProcessor
 
+from llmcompressor import oneshot
 from llmcompressor.modifiers.quantization import GPTQModifier
-from llmcompressor.transformers import oneshot
 from llmcompressor.transformers.tracing import TraceableLlavaForConditionalGeneration
 
 # Load model.