initial commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+best-model.ckpt filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,138 @@
+from transformers import T5Tokenizer, T5ForConditionalGeneration  
+
+from transformers import AdamW
+import pandas as pd
+import torch
+import pytorch_lightning as pl
+from pytorch_lightning.callbacks import ModelCheckpoint
+from torch.nn.utils.rnn import pad_sequence
+# from torch.utils.data import Dataset, DataLoader, random_split, RandomSampler, SequentialSampler
+
+pl.seed_everything(100)
+
+MODEL_NAME='t5-base'
+DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+INPUT_MAX_LEN = 128 
+OUTPUT_MAX_LEN = 128
+
+tokenizer = T5Tokenizer.from_pretrained(MODEL_NAME, model_max_length=512)
+
+class T5Model(pl.LightningModule):
+    
+    def __init__(self):
+        super().__init__()
+        self.model = T5ForConditionalGeneration.from_pretrained(MODEL_NAME, return_dict = True)
+
+        
+    def forward(self, input_ids, attention_mask, labels=None):
+        
+        output = self.model(
+        input_ids=input_ids, 
+        attention_mask=attention_mask, 
+        labels=labels
+        )
+        return output.loss, output.logits
+    
+    def training_step(self, batch, batch_idx):
+
+        input_ids = batch["input_ids"]
+        attention_mask = batch["attention_mask"]
+        labels= batch["target"]
+        loss, logits = self(input_ids , attention_mask, labels)
+
+        
+        self.log("train_loss", loss, prog_bar=True, logger=True)
+
+        return {'loss': loss}
+    
+    def validation_step(self, batch, batch_idx):
+        input_ids = batch["input_ids"]
+        attention_mask = batch["attention_mask"]
+        labels= batch["target"]
+        loss, logits = self(input_ids, attention_mask, labels)
+
+        self.log("val_loss", loss, prog_bar=True, logger=True)
+        
+        return {'val_loss': loss}
+
+    def configure_optimizers(self):
+        return AdamW(self.parameters(), lr=0.0001)
+
+train_model = T5Model.load_from_checkpoint('best-model.ckpt',map_location=DEVICE)
+train_model.freeze()
+
+def generate_response(question):
+
+    inputs_encoding =  tokenizer(
+        question,
+        add_special_tokens=True,
+        max_length= INPUT_MAX_LEN,
+        padding = 'max_length',
+        truncation='only_first',
+        return_attention_mask=True,
+        return_tensors="pt"
+        )
+
+    
+    generate_ids = train_model.model.generate(
+        input_ids = inputs_encoding["input_ids"],
+        attention_mask = inputs_encoding["attention_mask"],
+        max_length = INPUT_MAX_LEN,
+        num_beams = 4,
+        num_return_sequences = 1,
+        no_repeat_ngram_size=2,
+        early_stopping=True,
+        )
+
+    preds = [
+        tokenizer.decode(gen_id,
+        skip_special_tokens=True, 
+        clean_up_tokenization_spaces=True)
+        for gen_id in generate_ids
+    ]
+
+    return "".join(preds)
+
+
+import streamlit as st
+from streamlit_chat import message
+
+if 'generated' not in st.session_state:
+    st.session_state['generated'] = []
+if 'past' not in st.session_state:
+    st.session_state['past'] = []
+if 'messages' not in st.session_state:
+    st.session_state['messages'] = [
+        {"role": "system", "content": "You are a helpful assistant."}
+    ]
+
+
+
+# container for chat history
+response_container = st.container()
+# container for text box
+container = st.container()
+
+with container:
+    with st.form(key='my_form', clear_on_submit=True):
+        user_input = st.text_input("You:", key='input')
+        submit_button = st.form_submit_button(label='Send')
+    clear_button = st.button("Clear Conversation", key="clear")
+    # reset everything
+    if clear_button:
+        st.session_state['generated'] = []
+        st.session_state['past'] = []
+        st.session_state['messages'] = [
+            {"role": "system", "content": "You are a helpful assistant."}
+        ]
+
+    if submit_button and user_input:
+        output = generate_response(user_input)
+        st.session_state['past'].append(user_input)
+        st.session_state['generated'].append(output)
+
+if st.session_state['generated']:
+    with response_container:
+        for i in range(len(st.session_state['generated'])):
+            message(st.session_state["past"][i], is_user=True, key=str(i) + '_user')
+            message(st.session_state["generated"][i], key=str(i))

best-model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9efe3a4fe521ae871e5c1329b9c0a954e11b1b4c9cde89631b4addd3a6418942
+size 2675123319

requirements.txt

@@ -0,0 +1,7 @@
+transformers==4.27.4
+pandas==1.5.3
+torch==2.0.0
+pytorch-lightning==2.0.2
+sentencepiece==0.1.98
+streamlit==1.20.0
+streamlit-chat==0.0.2.2