5 papers
Saidzoda-CA-EmbeddingGemma-300M: One Small Embedder for Tajik, Kazakh, Uzbek and Kyrgyz
Tohir Saidzoda, Nekruz Maxudov, Bedil Karimov +5
The small open embedder EmbeddingGemma-300M, used as released, finds the right passage first for only 51.7% to 60.8% of Belebele questions in Tajik, Kazakh, Uzbek and Kyrgyz. We pr…
Saidzoda-Tajik-EmbeddingGemma-300M: Knowing Every Letter Is Not Reading Tajik
Tohir Saidzoda, Nekruz Maxudov, Bedil Karimov +5
EmbeddingGemma-300M is a small open embedder whose tokenizer represents every Tajik letter, and as released it is weak at Tajik retrieval: on our Tajik law test the right passage i…
Adapting Qwen3 to Tajik from 0.6B to 8B: Lower Text Loss Did Not Mean Better Understanding
Tohir Saidzoda, Madina Abdusalomzoda, Nasimjon Rajabov +7
Small LoRA adapters trained on Tajik news and books lowered Qwen3's Tajik text loss at every size we tried, from 0.6B to 8B, by 0.60 to 1.45 nats per token, but none of them improv…
Saidzoda-Tajik-E5-Large: Fine-Tuning a 560M Embedder for Tajik Retrieval
Tohir Saidzoda, Nekruz Maxudov, Bedil Karimov +5
Finding the passage that answers a question is the first step of most practical systems built on documents, and for Tajik we found no openly described model for it. We present Said…
Saidzoda-Tajik-LFM-2.6B: Adapting a 2.6B Hybrid Model to Tajik Tool Calling, and What Continued Pretraining Takes Away
Tohir Saidzoda, Nekruz Maxudov, Bedil Karimov +5
We release Saidzoda-Tajik-LFM-2.6B, a Tajik adaptation of the 2.6B-parameter hybrid model LFM2.5-2.6B-Base, built for tool calling in Tajik on modest hardware. The recipe has two s…