Update app.py

app.py

@@ -52,68 +52,69 @@ A: Let's find the row of year 2007, that's Row 3. Let's extract the numbers on R
 ## alpaca-lora
 
 # debugging...
-# assert (
-#     "LlamaTokenizer" in transformers._import_structure["models.llama"]
-# ), "LLaMA is now in HuggingFace's main branch.\nPlease reinstall it: pip uninstall transformers && pip install git+https://github.com/huggingface/transformers.git"
-# from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
-
-# tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/llama-7b-hf")
-
-# BASE_MODEL = "decapoda-research/llama-7b-hf"
-# LORA_WEIGHTS = "tloen/alpaca-lora-7b"
-
-# if torch.cuda.is_available():
-#     device = "cuda"
-# else:
-#     device = "cpu"
-
-# try:
-#     if torch.backends.mps.is_available():
-#         device = "mps"
-# except:
-#     pass
-
-# if device == "cuda":
-#     model = LlamaForCausalLM.from_pretrained(
-#         BASE_MODEL,
-#         load_in_8bit=False,
-#         torch_dtype=torch.float16,
-#         device_map="auto",
-#     )
-#     model = PeftModel.from_pretrained(
-#         model, LORA_WEIGHTS, torch_dtype=torch.float16, force_download=True
-#     )
-# elif device == "mps":
-#     model = LlamaForCausalLM.from_pretrained(
-#         BASE_MODEL,
-#         device_map={"": device},
-#         torch_dtype=torch.float16,
-#     )
-#     model = PeftModel.from_pretrained(
-#         model,
-#         LORA_WEIGHTS,
-#         device_map={"": device},
-#         torch_dtype=torch.float16,
-#     )
-# else:
-#     model = LlamaForCausalLM.from_pretrained(
-#         BASE_MODEL, device_map={"": device}, low_cpu_mem_usage=True
-#     )
-#     model = PeftModel.from_pretrained(
-#         model,
-#         LORA_WEIGHTS,
-#         device_map={"": device},
-#     )
-
-
-# if device != "cpu":
-#     model.half()
-# model.eval()
-# if torch.__version__ >= "2":
-#     model = torch.compile(model)
+assert (
+    "LlamaTokenizer" in transformers._import_structure["models.llama"]
+), "LLaMA is now in HuggingFace's main branch.\nPlease reinstall it: pip uninstall transformers && pip install git+https://github.com/huggingface/transformers.git"
+from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
+
+tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/llama-7b-hf")
+
+BASE_MODEL = "decapoda-research/llama-7b-hf"
+LORA_WEIGHTS = "tloen/alpaca-lora-7b"
+
+if torch.cuda.is_available():
+    device = "cuda"
+else:
+    device = "cpu"
+
+try:
+    if torch.backends.mps.is_available():
+        device = "mps"
+except:
+    pass
+
+if device == "cuda":
+    model = LlamaForCausalLM.from_pretrained(
+        BASE_MODEL,
+        load_in_8bit=False,
+        torch_dtype=torch.float16,
+        device_map="auto",
+    )
+    model = PeftModel.from_pretrained(
+        model, LORA_WEIGHTS, torch_dtype=torch.float16, force_download=True
+    )
+elif device == "mps":
+    model = LlamaForCausalLM.from_pretrained(
+        BASE_MODEL,
+        device_map={"": device},
+        torch_dtype=torch.float16,
+    )
+    model = PeftModel.from_pretrained(
+        model,
+        LORA_WEIGHTS,
+        device_map={"": device},
+        torch_dtype=torch.float16,
+    )
+else:
+    model = LlamaForCausalLM.from_pretrained(
+        BASE_MODEL, device_map={"": device}, low_cpu_mem_usage=True
+    )
+    model = PeftModel.from_pretrained(
+        model,
+        LORA_WEIGHTS,
+        device_map={"": device},
+    )
+
+
+if device != "cpu":
+    model.half()
+model.eval()
+if torch.__version__ >= "2":
+    model = torch.compile(model)
 
 
 ## FLAN-UL2
+# in dev...
 TOKEN = os.environ.get("API_TOKEN", None)
 API_URL = "https://api-inference.huggingface.co/models/google/flan-ul2"
 headers = {"Authorization": f"Bearer {TOKEN}"}