KoLLchIK/DeepSeek-R1-Distill-Qwen-1.5B-Russian_dataset

Adapter vs unsloth/DeepSeek-R1-Distill-Qwen-1.5B. KoLLchIK/DeepSeek-R1-Distill-Qwen-1.5B-Russian_dataset is a LoRA adapter, not full weights: rank 16, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 28 layers (196 adapted matrices). It modifies unsloth/DeepSeek-R1-Distill-Qwen-1.5B at load time.

On the Hub · Downloads on Model Pulse