ilotoki_thu/alpaca_lora_4bit
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

fix dependency

Browse Source
This commit is contained in:
John Smith
2023-04-26 17:17:59 +08:00
parent 42ef3484a9
commit 8e5cf08479
2 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
server/server.py
View File

@@ -1,8 +1,7 @@
from .. import autograd_4bit
import time
import torch
from ..autograd_4bit import load_llama_model_4bit_low_ram, Autograd4bitQuantLinear
from alpaca_lora_4bit.model_attn_mlp_patch import make_quant_attn, make_fused_mlp, inject_lora_layers
from autograd_4bit import load_llama_model_4bit_low_ram, Autograd4bitQuantLinear
from model_attn_mlp_patch import make_quant_attn, make_fused_mlp, inject_lora_layers
import zmq
from transformers import StoppingCriteria, StoppingCriteriaList
from io import BytesIO

2
text-generation-webui/generate_monkey_patch.py
View File

@@ -1,6 +1,6 @@
import modules.text_generation
from modules.text_generation import *
from alpaca_lora_4bit.server import _SentinelTokenStoppingCriteria
from server import _SentinelTokenStoppingCriteria
def generate_reply_patched(question, state, eos_token=None, stopping_strings=[]):
if shared.model_name == 'None' or shared.model is None: