Upload folder using huggingface_hub (#4)

- 566f2248d8d0ec1294d836f71f90d0b5fc87ccc7fb0f577d4983b8ae8439f963 (da7b967b403789f9a80a98efded3b1cb2df10ac0)
- 09957652f1fb4a5c496af0bf4ac70cad13dcf8e2b391213c65b848921e12407d (2acfabb4c9536654133ee489f660aa2b3517f0a5)

README.md

@@ -48,7 +48,7 @@ You can run the smashed model with these steps:
 0. Check cuda, torch, packaging requirements are installed. For cuda, check with `nvcc --version` and install with `conda install nvidia/label/cuda-12.1.0::cuda`. For packaging and torch, run `pip install packaging torch`.
 1. Install the `pruna-engine` available [here](https://pypi.org/project/pruna-engine/) on Pypi. It might take 15 minutes to install.
     ```bash
-   pip install pruna-engine[gpu] --extra-index-url https://pypi.nvidia.com --extra-index-url https://pypi.ngc.nvidia.com --extra-index-url https://prunaai.pythonanywhere.com/
+   pip install pruna-engine[gpu]==0.6.0 --extra-index-url https://pypi.nvidia.com --extra-index-url https://pypi.ngc.nvidia.com --extra-index-url https://prunaai.pythonanywhere.com/
     ```
 3. Download the model files using one of these three options. 
    - Option 1 - Use command line interface (CLI):

config.json

@@ -1 +1 @@
-{"pruners": "None", "pruning_ratio": "None", "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.0, "compilers": "['step_caching', 'tiling', 'diffusers2']", "static_batch": true, "static_shape": false, "controlnet": "None", "unet_dim": 4, "device": "cuda", "batch_size": 1, "max_batch_size": 1, "image_height": 512, "image_width": 512, "version": "1.5", "task": "txt2img", "weight_name": "None", "model_name": "prompthero/openjourney-v4", "save_load_fn": "stable_fast"}
+{"pruners": "None", "pruning_ratio": 0.0, "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.005, "compilers": "['diffusers2', 'tiling', 'step_caching']", "static_batch": true, "static_shape": false, "controlnet": "None", "unet_dim": 4, "device": "cuda", "batch_size": 1, "max_batch_size": 1, "image_height": 512, "image_width": 512, "version": "1.5", "task": "txt2img", "model_name": "prompthero/openjourney-v4", "weight_name": "None", "save_load_fn": "stable_fast"}

model/optimized_model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3b0fe81571333022fa53a600a13fb4550369fdfe0c8b8a863f15f759612af8
-size 2743426698
+oid sha256:78adab62013d3f6604ac619a045d1ebc1fdf64d21ce2647e6a964136c1b9112d
+size 2743426103

model/smash_config.json

@@ -1 +1 @@
-{"api_key": "pruna_c4c77860c62a2965f6bc281841ee1d7bd3", "verify_url": "http://johnrachwan.pythonanywhere.com", "smash_config": {"pruners": "None", "pruning_ratio": "None", "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.0, "compilers": "['step_caching', 'tiling', 'diffusers2']", "static_batch": true, "static_shape": false, "controlnet": "None", "unet_dim": 4, "device": "cuda", "cache_dir": ".models/optimized_model", "batch_size": 1, "max_batch_size": 1, "image_height": 512, "image_width": 512, "version": "1.5", "task": "txt2img", "weight_name": "None", "model_name": "prompthero/openjourney-v4", "save_load_fn": "stable_fast"}}
+{"api_key": "pruna_c4c77860c62a2965f6bc281841ee1d7bd3", "verify_url": "http://johnrachwan.pythonanywhere.com", "smash_config": {"pruners": "None", "pruning_ratio": 0.0, "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.005, "compilers": "['diffusers2', 'tiling', 'step_caching']", "static_batch": true, "static_shape": false, "controlnet": "None", "unet_dim": 4, "device": "cuda", "cache_dir": ".models/optimized_model", "batch_size": 1, "max_batch_size": 1, "image_height": 512, "image_width": 512, "version": "1.5", "task": "txt2img", "model_name": "prompthero/openjourney-v4", "weight_name": "None", "save_load_fn": "stable_fast"}}