How to reduce repetition with frequency_penalty

The frequency_penalty parameter helps you control how often the model repeats words or phrases.

• Positive values → penalize tokens that have already appeared → model is less likely to repeat itself.
• Negative values → encourage more repetition (rarely used).

How it works:

• After each token is generated, the model adjusts the probability of generating the same tokens again, based on how often they have already been used.
• This helps you create more varied and natural-sounding text.

Parameter details:

When to use frequency_penalty:

First, install the SDK:

pip install -Uqq sarvamai

Then use the following Python code:

from sarvamai import SarvamAI
# Initialize the SarvamAI client with your API key
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
# Example: Apply frequency_penalty to avoid repetition
response = client.chat.completions(
    model="sarvam-105b",
    messages=[
        {"role": "system", "content": "You are a travel blogger assistant."},
        {"role": "user", "content": "Write a paragraph about the beaches of Goa."}
    ],
    frequency_penalty=1.0  # Reduce repetitive phrases
)
# Receive assistant's reply as output
print(response.choices[0].message.content)