updated model

app.py

@@ -1,57 +1,58 @@
-# # from transformers import pipeline
+from transformers import pipeline
 # from transformers import T5Tokenizer, T5ForConditionalGeneration
-# import gradio as gr
+import gradio as gr
 
-# def pipe(input_text):
-#     tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-base")
-#     model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-base")
+def pipe(input_text):
+    # tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-base")
+    # model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-base")
 
-#     input_text = "reword for clarity" + input_text
-#     input_ids = tokenizer(input_text, return_tensors="pt").input_ids
+    # input_text = "reword for clarity" + input_text
+    # input_ids = tokenizer(input_text, return_tensors="pt").input_ids
 
-#     outputs = model.generate(input_ids)
-#     return tokenizer.decode(outputs[0])
+    # outputs = model.generate(input_ids)
+    # return tokenizer.decode(outputs[0])
 
-#     # model = pipeline(
-#     #     task='question-answering',
-#     #     model="google/flan-t5-base",
-#     # )
-#     # output = model(
-#     #     question="reword for clarity",
-#     #     context=input_text,
-#     # )
-#     # return output["answer"]
+    # Use a pipeline as a high-level helper
+    model = pipeline(
+        task='question-answering',
+        model="mistralai/Mistral-7B-Instruct-v0.3",
+    )
+    output = model(
+        question="reword for clarity",
+        context=input_text,
+    )
+    return output["answer"]
 
-# demo = gr.Interface(
-#     fn=pipe,
-#     inputs=gr.Textbox(lines=7),
-#     outputs="text",
-# )
-# demo.launch()
+demo = gr.Interface(
+    fn=pipe,
+    inputs=gr.Textbox(lines=7),
+    outputs="text",
+)
+demo.launch()
 
 
-# pip install -q transformers
-from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+# # pip install -q transformers
+# from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
-checkpoint = "CohereForAI/aya-101"
+# checkpoint = "CohereForAI/aya-101"
 
-tokenizer = AutoTokenizer.from_pretrained(checkpoint)
-aya_model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
+# tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+# aya_model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
 
-def generator(input_text):
-    inputs = tokenizer.encode("Translate to English: " + input_text, return_tensors="pt")
-    outputs = aya_model.generate(inputs, max_new_tokens=128)
-    return tokenizer.decode(outputs[0])
+# def generator(input_text):
+#     inputs = tokenizer.encode("Translate to English: " + input_text, return_tensors="pt")
+#     outputs = aya_model.generate(inputs, max_new_tokens=128)
+#     return tokenizer.decode(outputs[0])
 
-# # Turkish to English translation
-# tur_inputs = tokenizer.encode("Translate to English: Aya cok dilli bir dil modelidir.", return_tensors="pt")
-# tur_outputs = aya_model.generate(tur_inputs, max_new_tokens=128)
-# print(tokenizer.decode(tur_outputs[0]))
-# # Aya is a multi-lingual language model
+# # # Turkish to English translation
+# # tur_inputs = tokenizer.encode("Translate to English: Aya cok dilli bir dil modelidir.", return_tensors="pt")
+# # tur_outputs = aya_model.generate(tur_inputs, max_new_tokens=128)
+# # print(tokenizer.decode(tur_outputs[0]))
+# # # Aya is a multi-lingual language model
 
-demo = gr.Interface(
-    fn=generator,
-    inputs=gr.Textbox(lines=7),
-    outputs="text",
-)
-demo.launch()
+# demo = gr.Interface(
+#     fn=generator,
+#     inputs=gr.Textbox(lines=7),
+#     outputs="text",
+# )
+# demo.launch()