initial commit

app.py

@@ -1,29 +0,0 @@
-import gradio as gr
-import torch
-from model import Byt5LightningModule
-
-<<<<<<< HEAD
-<<<<<<< HEAD
-model = torch.load("model.pt", map_location=torch.device("cpu"), weights_only=True)
-=======
-model = torch.load("model.pt", map_location=torch.device("cpu"))
->>>>>>> 4524122 (initial commit)
-=======
-model = torch.load("model.pt", map_location=torch.device("cpu"), weights_only=True)
->>>>>>> 0efc206 (initial commit)
-model.eval()
-
-def predict(input_list):
-    with torch.no_grad():
-        tensor_input = torch.tensor([input_list], dtype=torch.float32)
-        output = model(tensor_input).item()
-    return f"Prediction: {output:.4f}"
-
-demo = gr.Interface(
-    fn=predict,
-    inputs=gr.Textbox(label="Input (Hex formatter Modbus request)"),
-    outputs="text",
-    examples=[["08090000000d001000250003060000ffffffff"]],
-)
-
-demo.launch()

model.py

@@ -1,26 +0,0 @@
-from lightning.pytorch import LightningModule
-from transformers import PreTrainedModel
-
-
-class Byt5LightningModule(LightningModule):
-
-    def __init__(self, model: PreTrainedModel):
-        super().__init__()
-        self._model = model
-
-    def forward(self, input_ids, attention_mask, decoder_attention_mask, labels=None):
-        output = self.model(
-            input_ids=input_ids,
-            attention_mask=attention_mask,
-            labels=labels,
-            decoder_attention_mask=decoder_attention_mask,
-        )
-        return output.loss, output.logits
-
-    @property
-    def model(self):
-        return self._model
-
-    @property
-    def tokenizer(self):
-        return self._tokenizer

requirements.txt

@@ -1,6 +0,0 @@
-lightning
-torch
-gradio
-transformers
-gradio
-transformers