GusPuffy
/

sentient-simulations-pydecompiler-3.7-6.7b-v0.9

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

GusPuffy commited on Mar 21

Commit

6783f61

•

1 Parent(s): 01f2fb9

Upload folder using huggingface_hub

Files changed (2) hide show

README.md +1 -1
decompile.py +1 -1

README.md CHANGED Viewed

@@ -71,7 +71,7 @@ python convert_pyc_to_bytecode.py directory_with_files
 2. Decompile the bytecode strings back to Python source code (This will take some time depending on how many files there are)
 ```
 conda activate pydecompiler-310
-python convert_pyc_to_bytecode.py directory_with_files
 ```
 Note that files over 15k token count are skipped.
 Files over 10k will most likely be truncated due to the context limit.

 2. Decompile the bytecode strings back to Python source code (This will take some time depending on how many files there are)
 ```
 conda activate pydecompiler-310
+python decompile.py directory_with_files
 ```
 Note that files over 15k token count are skipped.
 Files over 10k will most likely be truncated due to the context limit.

decompile.py CHANGED Viewed

@@ -5,7 +5,7 @@ from llama_cpp import Llama
 from util import create_prompt, is_bytecode_empty
 llm = Llama(
-    model_path="/home/guspuffy/projects/output-merged/GGUF/sentient-simulations-pydecompiler-3.7-6.7b-v0.9-q8_0.gguf",
     n_gpu_layers=-1,
     last_n_tokens_size=0,
     n_ctx=16384,

 from util import create_prompt, is_bytecode_empty
 llm = Llama(
+    model_path="sentient-simulations-pydecompiler-3.7-6.7b-v0.9-q8_0.gguf",
     n_gpu_layers=-1,
     last_n_tokens_size=0,
     n_ctx=16384,