[KongchangAI]
ModelTajik-E5-Large

Saidzoda-Tajik-E5-Large

A Tajik text embedding model fine-tuned from multilingual-e5-large-instruct, used for Tajik document retrieval. The model supports inference on a single consumer-grade GPU, making Tajik retrieval available without large-scale infrastructure.

Timeline (last 90 days)

Nov 3

Saidzoda-Tajik-E5-Large is a Tajik text embedding model built on multilingual-e5-large-instruct (560M parameters).

Unverified50%
Nov 3

Before Saidzoda-Tajik-E5-Large was released, there was no publicly described Tajik retrieval model.

Unverified50%
Nov 3

The 560M-parameter model can be run for inference on a single consumer-grade GPU.

Unverified50%
Nov 3

The training data contains 235,140 question-passage pairs, and training was run for one epoch.

Unverified50%
Nov 3

During training, another embedding model was used to select hard negatives, and English and Russian question-passage pairs were mixed in to prevent the model from forgetting these two languages.

Unverified50%
Nov 3

On legal texts the model has never seen, 93.6% of questions rank the correct passage in the top ten, compared with 80.2% for the baseline.

Unverified50%
Nov 3

On tax documents, 94.5% of questions rank the correct passage in the top ten, compared with 82.6% for the baseline.

Unverified50%
Nov 3

On the Belebele test set, Saidzoda-Tajik-E5-Large's top-10 retrieval accuracy improved from 92.2% for the baseline to 95.2%, but the confidence intervals overlap.

Unverified50%
Nov 3

On legal and tax questions in the same style as the training problems, Saidzoda-Tajik-E5-Large ties with Giga-Embeddings-3B.

Unverified50%
Nov 3

Training with bfloat16 caused the model to collapse.

Unverified50%

1 more timeline events

All Facts (11)

Source Articles