Moreza009 commited on
Commit
ccfca8d
1 Parent(s): 8d0b34d
Files changed (2) hide show
  1. app.py +3 -2
  2. requirements.txt +2 -0
app.py CHANGED
@@ -1,5 +1,6 @@
1
  import gradio as gr
2
-
 
3
  """
4
  For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
5
  """
@@ -7,7 +8,7 @@ For more information on `huggingface_hub` Inference API support, please check th
7
  from transformers import AutoTokenizer, AutoModelForCausalLM
8
 
9
  tokenizer = AutoTokenizer.from_pretrained("Moreza009/aya23-8b-double-quantized")
10
- model = AutoModelForCausalLM.from_pretrained("Moreza009/aya23-8b-double-quantized")
11
 
12
 
13
  def respond(
 
1
  import gradio as gr
2
+ import accelerate
3
+ import bitsandbytes
4
  """
5
  For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
6
  """
 
8
  from transformers import AutoTokenizer, AutoModelForCausalLM
9
 
10
  tokenizer = AutoTokenizer.from_pretrained("Moreza009/aya23-8b-double-quantized")
11
+ model = AutoModelForCausalLM.from_pretrained("Moreza009/aya23-8b-double-quantized",device_map="auto")
12
 
13
 
14
  def respond(
requirements.txt CHANGED
@@ -1,3 +1,5 @@
 
 
1
  torch
2
  transformers
3
  huggingface_hub==0.22.2
 
1
+ accelerate
2
+ bitsandbytes
3
  torch
4
  transformers
5
  huggingface_hub==0.22.2