AI4Bharat State Expert — Tamil Nadu

Fine-tuned Qwen3-1.7B on AI4Bharat Indic Languages dataset for Tamil Nadu. Trained at SRMIST Vadapalani AI4Bharat Tune-Athon (Feb 26, 2026). Checkpoint: saved.

Training

Param	Value
Base	Qwen3-1.7B 4-bit
Modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Splits	indic + conv + cult

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("kirithika-m/AI4Bharat-State-Expert-Tamil_Nadu")
tok = AutoTokenizer.from_pretrained("kirithika-m/AI4Bharat-State-Expert-Tamil_Nadu")

Merged FP16 model — no PEFT required.

Downloads last month: 6

Safetensors

Model size

2B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kirithika-m/AI4Bharat-State-Expert-Tamil_Nadu

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Adapter

(344)

this model