Training pro- removed monkeypatch references (#6695)

This commit is contained in:
FP HAM 2025-01-24 09:23:44 -05:00 committed by GitHub
parent 0485ff20e8
commit 5d6f3e6f92
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -557,12 +557,6 @@ def calc_trainable_parameters(model):
def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch_size: int, batch_size: int, epochs: int, learning_rate: str, lr_scheduler_type: str, lora_rank: int, lora_alpha: int, lora_dropout: float, cutoff_len: int, dataset: str, eval_dataset: str, format: str, eval_steps: int, raw_text_file: str, higher_rank_limit: bool, warmup_steps: int, optimizer: str, hard_cut_string: str, train_only_after: str, stop_at_loss: float, add_eos_token: bool, min_chars: int, report_to: str, precize_slicing_overlap: bool, add_eos_token_type: str, save_steps_under_loss: float, add_bos_token: bool, training_projection: str,sliding_window:bool,warmup_ratio:float, grad_accumulation: int,neft_noise_alpha:float):
if shared.args.monkey_patch:
from alpaca_lora_4bit.monkeypatch.peft_tuners_lora_monkey_patch import (
replace_peft_model_with_int4_lora_model
)
replace_peft_model_with_int4_lora_model()
global train_log_graph
global WANT_INTERRUPT
WANT_INTERRUPT = False
@ -600,10 +594,6 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
time.sleep(5)
if shared.args.loader == 'GPTQ-for-LLaMa' and not shared.args.monkey_patch:
yield "LoRA training with GPTQ-for-LLaMa requires loading with `--monkey-patch`", zero_pd
return
if cutoff_len <= 0 or micro_batch_size <= 0 or actual_lr <= 0 or lora_rank <= 0 or lora_alpha <= 0:
yield "Cannot input zeroes.", zero_pd
return
@ -865,15 +855,6 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
yield traceback.format_exc().replace('\n', '\n\n'), zero_pd
return
if shared.args.monkey_patch:
from alpaca_lora_4bit.autograd_4bit import Autograd4bitQuantLinear
from alpaca_lora_4bit.models import Linear4bitLt
for _, m in lora_model.named_modules():
if isinstance(m, Autograd4bitQuantLinear) or isinstance(m, Linear4bitLt):
if m.is_v1_model:
m.zeros = m.zeros.half()
m.scales = m.scales.half()
class Tracked():
def __init__(self):
self.current_steps = 0