Allow BNB Plugin to be Loaded Without PEFT Wrapping

[fabianlim]

This issue regards to the warnings that for QLoRA PeFT we should pass peft_config directly to SFTTrainer

• if no_peft_model: True then model_loader will simply load the BNB model, and some logic needed to set requires_agumentation: False
• peft wrapping will be delegated to trf.SFTTrainer
• add one test for this new flag in tests/test_peft_plugin

• in generate sample configurations update the CONFIGURATIONS and COMBINATIONS:

  CONFIGURATIONS = {
    KEY_AUTO_GPTQ: "plugins/accelerated-peft/configs/autogptq.yaml",
    KEY_BNB_NF4: (
        "plugins/accelerated-peft/configs/bnb.yaml",
        [("peft.quantization.bitsandbytes.quant_type", "nf4")],
    ),
   KEY_BNB_NF4_BASELINE: (
        "plugins/accelerated-peft/configs/bnb.yaml",
        [
            ("peft.quantization.bitsandbytes.quant_type", "nf4"), 
           ("peft.quantization.bitsandbytes.no_peft_model", True), 
         ],
    ),
  }
  
  COMBINATIONS = [
    ("accelerated-peft-autogptq", (KEY_AUTO_GPTQ,)),
    ("accelerated-peft-bnb-nf4", (KEY_BNB_NF4,)),
    ("baseline-bnb-nf4", (KEY_BNB_NF4_BASELINE,)),
  ]

• regenerate the benches, update the CSV and the README

configs/bnb.yaml

add a new flag no_peft_model

# PEFT-related acceleration
peft:

  # quantization-releated acceleration
  # e.g., kernels for quantized base weights
  quantization: 

    # For loading BitsAndBytes quantized layers
    # to serve as 4bit base-weights for LoRA PEFT-tuning.
    # NOTE: currently AutoGPTQ is not properly integrated into huggingface /
    # bitsandbytes, thus recommended quant_type to be either "nf4"
    # or "fp4".
    # bitsandbytes:
    bitsandbytes:
      quant_type: nf4 

      # If True, then no get_peft_model and prepare_model_for_kbit_training
      # will be called. 
      no_peft_model: False

[fabianlim]

@achew010 note that we put in a comment in the main README

Huggingface BNB QLoRA numbers taken with legacy approaches, but we are aware of https://github.com/foundation-model-stack/fms-acceleration/issues/10 and will update our benches. The above includes numbers using fusedOps-and-kernels and actual impl coming soon, see below.

Now that this issue is closed, that comment should be removed.