Hugging Face's logo

Spaces:
liuhaotian
/
LLaVA-1.6
Runtime error

App Files Community
6
liuhaotian commited on
Commit
1c1b839
·
verified ·
1 Parent(s): ff6a08f

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -5
app.py CHANGED
@@ -68,11 +68,11 @@ if __name__ == "__main__":
68
 
69
  ONLY WORKS WITH GPU! By default, we load the model with 4-bit quantization to make it fit in smaller hardwares. Set the environment variable `bits` to control the quantization.
70
 
71
- Set the environment variable `model` to change the model, and switch hardware accordingly:
72
- [`liuhaotian/llava-v1.6-mistral-7b`](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b)
73
- [`liuhaotian/llava-v1.6-vicuna-7b`](https://huggingface.co/liuhaotian/llava-v1.6-vicuna-7b)
74
- [`liuhaotian/llava-v1.6-vicuna-13b`](https://huggingface.co/liuhaotian/llava-v1.6-vicuna-13b)
75
- [`liuhaotian/llava-v1.6-34b`](https://huggingface.co/liuhaotian/llava-v1.6-34b)
76
  """
77
 
78
  print(f"args: {gws.args}")
 
68
 
69
  ONLY WORKS WITH GPU! By default, we load the model with 4-bit quantization to make it fit in smaller hardwares. Set the environment variable `bits` to control the quantization.
70
 
71
+ Set the environment variable `model` to change the model:
72
+ [`liuhaotian/llava-v1.6-mistral-7b`](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b),
73
+ [`liuhaotian/llava-v1.6-vicuna-7b`](https://huggingface.co/liuhaotian/llava-v1.6-vicuna-7b),
74
+ [`liuhaotian/llava-v1.6-vicuna-13b`](https://huggingface.co/liuhaotian/llava-v1.6-vicuna-13b),
75
+ [`liuhaotian/llava-v1.6-34b`](https://huggingface.co/liuhaotian/llava-v1.6-34b).
76
  """
77
 
78
  print(f"args: {gws.args}")