davidberenstein1957 commited on
Commit
3da5344
·
verified ·
1 Parent(s): 0859f48

Add files using upload-large-folder tool

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  2. dtype_info.json +1 -0
README.md CHANGED
@@ -13,7 +13,7 @@ This model was created using the [pruna](https://github.com/PrunaAI/pruna) libra
13
  First things first, you need to install the pruna library:
14
 
15
  ```bash
16
- pip install "pruna[full]"
17
  ```
18
 
19
  You can then load this model using the following code:
@@ -21,9 +21,7 @@ You can then load this model using the following code:
21
  ```python
22
  from pruna import PrunaModel
23
 
24
- loaded_model = PrunaModel.from_hub(
25
- "dataset-viber/stable-diffusion-v1-4-smashed"
26
- )
27
  ```
28
 
29
  After loading the model, you can use the inference methods of the original model.
@@ -58,7 +56,7 @@ The compression configuration of the model is stored in the `smash_config.json`
58
 
59
  ## Model Configuration
60
 
61
- The configuration of the model is stored in the `*.json` files.
62
 
63
  ```bash
64
  {
@@ -99,6 +97,9 @@ The configuration of the model is stored in the `*.json` files.
99
  "diffusers",
100
  "AutoencoderKL"
101
  ]
 
 
 
102
  }
103
  }
104
  ```
 
13
  First things first, you need to install the pruna library:
14
 
15
  ```bash
16
+ pip install pruna
17
  ```
18
 
19
  You can then load this model using the following code:
 
21
  ```python
22
  from pruna import PrunaModel
23
 
24
+ loaded_model = PrunaModel.from_hub("dataset-viber/stable-diffusion-v1-4-smashed")
 
 
25
  ```
26
 
27
  After loading the model, you can use the inference methods of the original model.
 
56
 
57
  ## Model Configuration
58
 
59
+ The configuration of the model is stored in the `config.json` file.
60
 
61
  ```bash
62
  {
 
97
  "diffusers",
98
  "AutoencoderKL"
99
  ]
100
+ },
101
+ "dtype_info": {
102
+ "dtype": "float32"
103
  }
104
  }
105
  ```
dtype_info.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"dtype": "float32"}