update requirements

app.py

@@ -1,18 +1,13 @@
 import gradio as gr
 
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers import TextStreamer
 
 import spaces
 
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16
-)
-
 # Load model and tokenizer
-model = AutoModelForCausalLM.from_pretrained("Rorical/0-roleplay", return_dict=True, trust_remote_code=True).to(dtype=torch.float16)
-model = model.to(device="cuda")
+model = AutoModelForCausalLM.from_pretrained("Rorical/0-roleplay", return_dict=True, trust_remote_code=True, load_in_4bit=True)
 tokenizer = AutoTokenizer.from_pretrained("Rorical/0-roleplay", trust_remote_code=True)
 tokenizer.chat_template = "{% for message in messages %}{{'' + ((message['role'] + '\n') if message['role'] != '' else '') + message['content'] + '' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '星野\n' }}{% endif %}"
 

requirements.txt

@@ -1,8 +1,8 @@
 accelerate
+transformers==4.34.0
 bitsandbytes
 timm
 einops
 torch
 torchvision
-Pillow
-transformers
+Pillow