ibm-granite/granite-3.3-2b-instruct · Token Overflow Error

Hi,
I am currently building a Gen AI model which can summarize the uploaded documents or can do QA based on user intent. However, I am facing issue with the Summarization part. I am always getting "Token indices sequence length is longer than the specified maximum sequence length for this model". Please help in correcting my code. I am using "ibm-granite/granite-3.3-2b-instruct" for this model. Please help I am stuck for past few weeks in this only.

Also, pasting my get_summary function for your reference:

def get_summary(text: str) -> str:
splitter = RecursiveCharacterTextSplitter(chunk_size=3000, chunk_overlap=40)
chunks = splitter.split_text(text)
docs = [Document(page_content=c) for c in chunks]

print(f"📦 Chunks: {len(chunks)}")
for i,c in enumerate(chunks,1):
    print(f"   Chunk {i}: ~{len(c.split())} words")

# 2. Prompts
map_prompt = PromptTemplate(
    input_variables=["text"],
    template="""

<|system|>
You are a concise assistant for banking docs.
<|user|>
Summarize in under 400 tokens, no hallucinations:
{text}
<|assistant|>
"""
)
combine_prompt = PromptTemplate(
input_variables=["text"],
template="""
<|system|>
You are a banking reports summarization expert.
<|user|>
Combine chunk summaries into one concise summary (≤800 tokens), strictly factual:
{text}
<|assistant|>
"""
)

# 3. Summarize
chain = load_summarize_chain(
    llm=llm,
    chain_type="map_reduce",
    map_prompt=map_prompt,
    combine_prompt=combine_prompt
)
return chain.invoke(docs)["output_text"]