Rename GPTQArgs and FP8Args

Signed-off-by: Thara Palanivel <[email protected]>

Author: tharapalanivel

.spellcheck-en-custom.txt

@@ -26,10 +26,11 @@ eval
 fms
 fp
 FP
+FP8Arguments
 frac
 gptq
 GPTQ
-GPTQArgs
+GPTQArguments
 graphviz
 GPTQ
 hyperparameters

examples/FP8_QUANT/README.md

@@ -27,7 +27,7 @@ This is an example of mature FP8, which under the hood leverages some functional
 ## QuickStart
 This end-to-end example utilizes the common set of interfaces provided by `fms_mo` for easily applying multiple quantization algorithms with FP8 being the focus of this example. The steps involved are:
 
-1. **FP8 quantization through CLI**. Other arguments could be found here [FP8Args](../../fms_mo/training_args.py#L84).
+1. **FP8 quantization through CLI**. Other arguments could be found here [FP8Arguments](../../fms_mo/training_args.py#L84).
 
     ```bash
     python -m fms_mo.run_quant \
@@ -100,7 +100,7 @@ This end-to-end example utilizes the common set of interfaces provided by `fms_m
     tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path)
     ```
 
-2. Quantization setting is provided using `QuantizationModifier`, additional settings can be found in [FP8Args](../../fms_mo/training_args.py#L84).
+2. Quantization setting is provided using `QuantizationModifier`, additional settings can be found in [FP8Arguments](../../fms_mo/training_args.py#L84).
 
     ```python
     recipe = QuantizationModifier(

examples/GPTQ/README.md

@@ -32,7 +32,7 @@ This end-to-end example utilizes the common set of interfaces provided by `fms_m
 > - Tokenized data will be saved in `<path_to_save>_train` and `<path_to_save>_test`
 > - If you have trouble downloading Llama family of models from Hugging Face ([LLama models require access](https://www.llama.com/docs/getting-the-models/hugging-face/)), you can use `ibm-granite/granite-8b-code` instead
 
-2. **Quantize the model** using the data generated above, the following command will kick off the quantization job (by invoking `auto_gptq` under the hood.) Additional acceptable arguments can be found here in [GPTQArgs](../../fms_mo/training_args.py#L127).
+2. **Quantize the model** using the data generated above, the following command will kick off the quantization job (by invoking `auto_gptq` under the hood.) Additional acceptable arguments can be found here in [GPTQArguments](../../fms_mo/training_args.py#L127).
 
     ```bash
     python -m fms_mo.run_quant \

fms_mo/run_quant.py

@@ -39,8 +39,8 @@
 from fms_mo.training_args import (
     DataArguments,
     FMSMOArguments,
-    FP8Args,
-    GPTQArgs,
+    FP8Arguments,
+    GPTQArguments,
     ModelArguments,
 )
 from fms_mo.utils.import_utils import available_packages
@@ -52,8 +52,8 @@ def quantize(
     model_args: ModelArguments,
     data_args: DataArguments,
     fms_mo_args: FMSMOArguments,
-    gptq_args: GPTQArgs,
-    fp8_args: FP8Args,
+    gptq_args: GPTQArguments,
+    fp8_args: FP8Arguments,
     quant_method: str,
     output_dir: str,
 ):
@@ -65,9 +65,9 @@ def quantize(
         data_args (fms_mo.training_args.DataArguments): Data arguments to be used when loading the
             tokenized dataset
         fms_mo_args (fms_mo.training_args.FMSMOArguments): Parameters to use for PTQ quantization
-        gptq_args (fms_mo.training_args.GPTQArgs): Parameters to use for GPTQ quantization
-        fp8_args (fms_mo.training_args.FP8Args): Parameters to use for FP8 quantization
-        quant_method (str): Quantization technique, options are gptq and fp8
+        gptq_args (fms_mo.training_args.GPTQArguments): Parameters to use for GPTQ quantization
+        fp8_args (fms_mo.training_args.FP8Arguments): Parameters to use for FP8 quantization
+        quant_method (str): Quantization technique, options are gptq, fp8 and dq
         output_dir (str) Output directory to write to
     """
 
@@ -106,7 +106,7 @@ def run_gptq(model_args, data_args, gptq_args, output_dir):
             the model
         data_args (fms_mo.training_args.DataArguments): Data arguments to be used when loading the
             tokenized dataset
-        gptq_args (fms_mo.training_args.GPTQArgs): Parameters to use for GPTQ quantization
+        gptq_args (fms_mo.training_args.GPTQArguments): Parameters to use for GPTQ quantization
         output_dir (str) Output directory to write to
     """
 
@@ -167,7 +167,7 @@ def run_fp8(model_args, data_args, fp8_args, output_dir):
             the model
         data_args (fms_mo.training_args.DataArguments): Data arguments to be used when loading the
             tokenized dataset
-        fp8_args (fms_mo.training_args.FP8Args): Parameters to use for FP8 quantization
+        fp8_args (fms_mo.training_args.FP8Arguments): Parameters to use for FP8 quantization
         output_dir (str) Output directory to write to
     """
 
@@ -207,8 +207,8 @@ def main():
             ModelArguments,
             DataArguments,
             FMSMOArguments,
-            GPTQArgs,
-            FP8Args,
+            GPTQArguments,
+            FP8Arguments,
         )
     )
 

fms_mo/training_args.py

@@ -115,7 +115,7 @@ class FMSMOArguments:
 
 
 @dataclass
-class GPTQArgs:
+class GPTQArguments:
     """Dataclass for GPTQ related arguments that will be used by auto-gptq."""
 
     bits: int = field(default=4, metadata={"choices": [2, 3, 4, 8]})
@@ -133,7 +133,7 @@ class GPTQArgs:
 
 
 @dataclass
-class FP8Args:
+class FP8Arguments:
     """Dataclass for FP8 related arguments that will be used by llm-compressor."""
 
     targets: str = field(default="Linear")