Tirth2109
/

qwen-indic-v1

Feature Extraction

sentence-transformers

text-embeddings-inference

Model card Files Files and versions

qwen-indic-v1

LoRA fine-tune of Qwen/Qwen3-Embedding-8B on Indic-language data using a 3-stage contrastive recipe with teacher preservation. Last-token pooling, L2-normalized embeddings.

Base model: Qwen/Qwen3-Embedding-8B
Pooling: last-token
Languages: 22 scheduled Indic languages
Training data: train splits only; decontaminated against MTEB test sets

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

·

Model tree for Tirth2109/qwen-indic-v1

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-Embedding-8B

Finetuned

(36)

this model