Instructions to use navyam-ai/navya-1c-sft-dpo-grpo-reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use navyam-ai/navya-1c-sft-dpo-grpo-reasoning with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="navyam-ai/navya-1c-sft-dpo-grpo-reasoning")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("navyam-ai/navya-1c-sft-dpo-grpo-reasoning")
model = AutoModelForCausalLM.from_pretrained("navyam-ai/navya-1c-sft-dpo-grpo-reasoning", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use navyam-ai/navya-1c-sft-dpo-grpo-reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "navyam-ai/navya-1c-sft-dpo-grpo-reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "navyam-ai/navya-1c-sft-dpo-grpo-reasoning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/navyam-ai/navya-1c-sft-dpo-grpo-reasoning

SGLang

How to use navyam-ai/navya-1c-sft-dpo-grpo-reasoning with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "navyam-ai/navya-1c-sft-dpo-grpo-reasoning" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "navyam-ai/navya-1c-sft-dpo-grpo-reasoning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "navyam-ai/navya-1c-sft-dpo-grpo-reasoning" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "navyam-ai/navya-1c-sft-dpo-grpo-reasoning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use navyam-ai/navya-1c-sft-dpo-grpo-reasoning with Docker Model Runner:
```
docker model run hf.co/navyam-ai/navya-1c-sft-dpo-grpo-reasoning
```

Navya-1c-sft-dpo-grpo-reasoning

A reasoning-distilled variant of the India-first Navya-1c chat model (1.31B params).

This is the 1.31B Navya-1c lineage — from-scratch base (~103B tokens + WSD cooldown on 8×H100) → SFT → DPO → GRPO → reasoning distillation — taught to answer with an explicit <think>…</think> chain-of-thought before its final answer. The reasoning teacher was a locally-run deepseek-r1:14b (R1-Distill) over India personal-finance prompts.

Output format:

<think>
step-by-step reasoning about the question
</think>

final answer

⚠️ Status: research proof-of-concept

This checkpoint demonstrates the <think> reasoning habit but was distilled on a small purpose-built corpus and overfits it (train loss → ~0, validation loss rising). It reliably produces the reasoning format, but is not a production-grade reasoning model — treat it as a research PoC. The flagship production chat model remains navyam-ai/navya-1c-sft.

Research model — not investment advice. Small model; verify anything consequential.

Intended use

India personal-finance Q&A (savings, SIPs, loans, credit, insurance, tax) in English and Hindi/Hinglish, with visible step-by-step reasoning.

Details

Params: 1.31B · Author: Navyam AI (Bachatt)
Architecture: Llama-recipe — dim 2048, 26 layers, GQA 16/4 heads, SwiGLU, RMSNorm, RoPE, tied embeddings, 64k vocab, 4096 context
Tokenizer: custom tokenizer-v0.3-64k
Chat template: navya-chat-v1 (role tokens <|reserved_0..4|>)
Lineage: navya-1c (base) → sft → dpo → grpo → reasoning distillation (deepseek-r1:14b teacher)
Source: https://github.com/bachatt-app/navyam-gpt
License: Apache-2.0

Downloads last month: 123

Safetensors

Model size

1B params

Tensor type

F32

Model tree for navyam-ai/navya-1c-sft-dpo-grpo-reasoning

Base model

navyam-ai/navya-1c-sft

Finetuned

(1)

this model

Collection including navyam-ai/navya-1c-sft-dpo-grpo-reasoning

Navya-1

Collection

India-first financial LMs from scratch (100M-1.31B), base + SFT chat. navya-1c-sft powers navyam.ai. • 6 items • Updated 3 days ago