Upload 2 files

handler.py

@@ -0,0 +1,41 @@
+from typing import Dict, List, Any
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import transformers
+import torch
+
+# dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.float16
+
+class EndpointHandler:
+    def __init__(self, path=""):
+
+        tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
+        tokenizer.padding_side = "left"
+        tokenizer.pad_token = tokenizer.unk_token
+        model = AutoModelForCausalLM.from_pretrained(
+            path,
+            return_dict=True,
+            device_map="auto",
+            load_in_8bit=True,
+            torch_dtype=torch.bfloat16,
+            trust_remote_code=True
+        )
+
+        generation_config = model.generation_config
+        generation_config.max_new_tokens = 200
+        generation_config.temperature = 0.7
+        generation_config.top_p = 0.7
+        generation_config.num_return_sequences = 1
+        generation_config.pad_token_id = tokenizer.pad_token_id
+        generation_config.eos_token_id = tokenizer.eos_token_id
+        self.generation_config = generation_config
+
+        self.pipeline = transformers.pipeline(
+            "text-generation",
+            model=model,
+            tokenizer=tokenizer
+        )
+
+    def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
+        prompt = data.pop("inputs", data)
+        result = self.pipeline(prompt, generation_config=self.generation_config)
+        return result

requirements.txt

@@ -0,0 +1,7 @@
+torch
+transformers
+bitsandbytes
+accelerate
+loralib
+einops
+datasets