India2B parameters10 Indian languagesOpen weights

Explore Sarvam-1

Use Sarvam-1 for generation, translation, summarization, and language understanding across ten Indian languages and English.

Model

sarvamai/sarvam-1

Input

Configure your request

text_inputs

Passed directly as TextGenerationPipeline text_inputs. Enter raw text or a JSON chat-message array when the tokenizer has a chat template.

Parameters

return_full_text return_text return_tensors clean_up_tokenization_spaces continue_final_message

handle_long_generation

prefix

Sample outputDisable for greedy, deterministic decoding.

Temperature

Top P

Top K

Min P

Relative probability floor; zero disables it.

Typical P

Maximum output tokens

Input tokens and generated tokens together must fit the 8,192 token context window.

Minimum output tokens

Repetition penalty

No-repeat n-gram size

Beam count

Use KV cache

Length penalty

Early stopping

num_return_sequences