fix the contiguous kernel error and prep for eora release

ModelCloud · Mar 3, 2025 · dc6f0f1 · dc6f0f1
1 parent bf9aa2f
commit dc6f0f1
Show file tree

Hide file tree

Showing 2 changed files with 0 additions and 199 deletions.
diff --git a/gptqmodel/eora/eora_load_and_infer.py b/gptqmodel/eora/eora_load_and_infer.py
@@ -35,22 +35,3 @@ def test_load(backend: BACKEND):
     print(f"Result: {result}")
     assert "paris" in result.lower()
 
-
-# os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"    
-# quant_model_path = "/home/shihyangl/gptqmodel_save/Llama-3.2-1B-gptqmodel-4bit"
-# lora_path = "/home/shihyangl/llama3.2-1b-4bit-group128-eora-rank128-arc/adapter_model.safetensors" #"sliuau/llama3.2-1b-4bit-group128-eora-rank128-arc/blob/main/adapter_model.safetensors" #"sliuau/llama3.2-1b-4bit-group128-eora-rank128-arc"
-
-# adapter = EoRA(lora_path=lora_path, rank=128)
-
-# model = GPTQModel.load(
-#     quant_model_path,
-#     adapter=adapter,
-#     backend=BACKEND.TORCH,
-#     device_map="auto",
-# )
-
-# # print(model)
-# tokens = model.generate("Capital of France is")[0]
-# result = model.tokenizer.decode(tokens)
-# print(f"Result: {result}")
-# assert "paris" in result.lower()
diff --git a/llama.py b/llama.py