Upload handler.py

handler.py

@@ -0,0 +1,39 @@
+
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from peft import PeftModel
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        base_model_id = "mistralai/Mistral-7B-v0.1"
+        bnb_config = BitsAndBytesConfig(
+            load_in_4bit=True,
+            bnb_4bit_use_double_quant=True,
+            bnb_4bit_quant_type="nf4",
+            bnb_4bit_compute_dtype=torch.bfloat16
+        )
+        
+        base_model = AutoModelForCausalLM.from_pretrained(
+            base_model_id,  # Mistral, same as before
+            quantization_config=bnb_config,  # Same quantization config as before
+            device_map="auto",
+            trust_remote_code=True,
+           # use_auth_token=True
+        )
+        
+        tokenizer = AutoTokenizer.from_pretrained(base_model_id, add_bos_token=True, trust_remote_code=True)
+
+        ft_model = PeftModel.from_pretrained(base_model, "./checkpoint-100")
+
+
+    
+    def __call__(self, eval_prompt):
+
+        model_input = tokenizer(eval_prompt, return_tensors="pt").to("cuda")
+
+        ft_model.eval()
+        with torch.no_grad():
+            prediction = (tokenizer.decode(ft_model.generate(**model_input, max_new_tokens=100, repetition_penalty=1.15)[0], skip_special_tokens=True))
+
+        
+        return prediction