Upload 2 files

handler.py

@@ -0,0 +1,39 @@
+from typing import  Dict, List, Any
+from ctransformers import AutoModelForCausalLM
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        model_id = "djomo/MISTRALllux1000-7b-v5-GGUF"
+        model_file="mistralllux1000-7b-v5.gguf.q5_k_m.bin"
+        config = {'context_length' : 3048,'max_new_tokens': 856, 'repetition_penalty': 1.1,'temperature': 0.1, 'stream': True}
+        llm = AutoModelForCausalLM.from_pretrained(
+                                           model_id,
+                                           model_file=model_file,
+                                           model_type="mistral",
+                                           gpu_layers=130,#50 #110
+                                           **config
+                                           )
+        self.pipeline = llm
+
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        """
+        Args:
+            data (:obj:):
+                includes the input data and the parameters for the inference.
+        Return:
+            A :obj:`list`:. The object returned should be a list of one list like [[{"label": 0.9939950108528137}]] containing :
+                - "label": A string representing what the label/class is. There can be multiple labels.
+                - "score": A score between 0 and 1 describing how confident the model is for this label/class.
+        """
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+
+        # pass inputs with all kwargs in data
+        if parameters is not None:
+            prediction = self.pipeline(inputs, stream=False)
+        else:
+            prediction = self.pipeline(inputs, stream=False)
+        # postprocess the prediction
+        return prediction

requirements.txt

@@ -0,0 +1 @@
+ctransformers==0.2.27