Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,44 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.prompts import PromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from langchain.memory import ConversationSummaryMemory
+from langchain_huggingface import HuggingFacePipeline
+from langchain_core.runnables import RunnableSequence
+import gradio as gr
+
+# Load model
+model_id = "google/gemma-2b"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+# Text generation pipeline
+generator = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=100,
+    do_sample=True,
+    temperature=0.7
+)
+
+
+
+# LangChain wrapper
+llm = HuggingFacePipeline(pipeline=generator)
+
+# Prompt template
+prompt = ChatPromptTemplate.from_messages([
+     ("system", "You are a helpful assistant. Explain the following code clearly:\n\n{code}")
+])
+
+# Runnable sequence instead of LLMChain
+chain = prompt | llm | StrOutputParser()
+
+
+# Gradio interface
+def generate_answer(input_code):
+    result = chain.invoke({"code":input_code })
+    return result
+
+gr.Interface(fn=generate_answer, inputs="text", outputs="text", title="Gemma 2B Code Explainer").launch()