navya-1b-sft-v9
Navya is an India-first financial foundation model family, trained from scratch on an India-first corpus (finance + English + Hindi/Hinglish and other Indian languages), custom 64k tokenizer.
| Parameters | 337M |
| Training tokens | not disclosed |
| Trained | 2026 |
| Type | chat (SFT) |
| Author | Navyam AI (Bachatt) |
| License | Apache-2.0 |
| Code | https://github.com/bachatt-app/navyam-gpt |
337M base instruction-tuned (SFT) on the India-finance corpus. Prior model served on navyam.ai.
Intended use: India personal-finance Q&A. Research model — not investment advice.
Chat template
Role tokens <|reserved_0..4|> (system/user/assistant/tool/end_turn); generation stops on <|reserved_4|> and <|eos|>.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("navyam-ai/navya-1b-sft-v9")
model = AutoModelForCausalLM.from_pretrained("navyam-ai/navya-1b-sft-v9")