Add application file

app.py

@@ -52,7 +52,9 @@ elif device == "mps":
     )
 else:
     model = LlamaForCausalLM.from_pretrained(
-        BASE_MODEL, device_map={"": device}, low_cpu_mem_usage=True
+        BASE_MODEL, 
+        device_map={"": device}, 
+        low_cpu_mem_usage=True
     )
     model = PeftModel.from_pretrained(
         model,
@@ -65,16 +67,16 @@ print("Model: " + str(model))
 def generate_prompt(instruction, input=None):
     if input:
         return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
-### Instruction:
-{instruction}
-### Input:
-{input}
-### Response:"""
+                ### Instruction:
+                {instruction}
+                ### Input:
+                {input}
+                ### Response:"""
     else:
         return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
-### Instruction:
-{instruction}
-### Response:"""
+                ### Instruction:
+                {instruction}
+                ### Response:"""
 
 if device != "cpu":
     model.half()
@@ -89,8 +91,8 @@ def evaluate(
     temperature=0.1,
     top_p=0.75,
     top_k=40,
-    num_beams=4,
-    max_new_tokens=128,
+    num_beams=2,
+    max_new_tokens=64,
     **kwargs,
 ):
     prompt = generate_prompt(instruction, input)

requirements.txt

@@ -1,12 +1,9 @@
-accelerate
-appdirs
+datasets
 loralib
+sentencepiece
+git+https://github.com/huggingface/transformers.git
+accelerate
 bitsandbytes
-black
-black[jupyter]
-datasets
-fire
 git+https://github.com/huggingface/peft.git
-transformers>=4.28.0
-sentencepiece
 gradio
+scipy