mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Remove GPTQ-for-LLaMa monkey patch support

Browse source 
AutoGPTQ will be the preferred GPTQ LoRa loader in the future.
This commit is contained in:
jllllll 2023-08-09 23:59:04 -05:00
parent bee73cedbd
commit e3d3565b2a
No known key found for this signature in database
GPG key ID: 7FCD00C417935797
6 changed files with 0 additions and 103 deletions
Download patch file Download diff file Expand all files Collapse all files

43
modules/monkey_patch_gptq_lora.py
View file

@ -1,43 +0,0 @@
# Copied from https://github.com/johnsmith0031/alpaca_lora_4bit
import sys
from pathlib import Path
sys.path.insert(0, str(Path("repositories/alpaca_lora_4bit")))
import autograd_4bit
from amp_wrapper import AMPWrapper
from autograd_4bit import (
Autograd4bitQuantLinear,
load_llama_model_4bit_low_ram
)
from monkeypatch.peft_tuners_lora_monkey_patch import (
Linear4bitLt,
replace_peft_model_with_gptq_lora_model
)
from modules import shared
from modules.GPTQ_loader import find_quantized_model_file
replace_peft_model_with_gptq_lora_model()
def load_model_llama(model_name):
config_path = str(Path(f'{shared.args.model_dir}/{model_name}'))
model_path = str(find_quantized_model_file(model_name))
model, tokenizer = load_llama_model_4bit_low_ram(config_path, model_path, groupsize=shared.args.groupsize, is_v1_model=False)
for n, m in 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()
m.bias = m.bias.half()
autograd_4bit.use_new = True
autograd_4bit.auto_switch = True
model.half()
wrapper = AMPWrapper(model)
wrapper.apply_generate()
return model, tokenizer

23
modules/training.py
View file

@ -270,12 +270,6 @@ 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, overlap_len: int, newline_favor_len: int, 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):
if shared.args.monkey_patch:
from monkeypatch.peft_tuners_lora_monkey_patch import (
replace_peft_model_with_gptq_lora_model
)
replace_peft_model_with_gptq_lora_model()
global WANT_INTERRUPT
WANT_INTERRUPT = False
@ -307,15 +301,6 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
time.sleep(5)
if shared.args.wbits > 0 and not shared.args.monkey_patch:
yield "LoRA training with GPTQ models requires loading with `--monkey-patch`"
return
elif not (shared.args.load_in_8bit or shared.args.load_in_4bit) and shared.args.wbits <= 0:
yield "It is highly recommended you use `--load-in-8bit` for LoRA training. *(Will continue anyway in 2 seconds, press `Interrupt` to stop.)*"
logger.warning("It is highly recommended you use `--load-in-8bit` for LoRA training.")
time.sleep(2) # Give it a moment for the message to show in UI before continuing
if cutoff_len <= 0 or micro_batch_size <= 0 or batch_size <= 0 or actual_lr <= 0 or lora_rank <= 0 or lora_alpha <= 0:
yield "Cannot input zeroes."
return
@ -520,14 +505,6 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
yield traceback.format_exc().replace('\n', '\n\n')
return
if shared.args.monkey_patch:
for n, m in lora_model.named_modules():
if '4bit' in str(type(m)):
if m.is_v1_model:
m.zeros = m.zeros.half()
m.scales = m.scales.half()
class Tracked():
def __init__(self):
self.current_steps = 0