BachDaThan/Qwen2.5-Coder-7B-Vietnamese-LoRA-GGUF

Adapter vs khoin68/Qwen2.5-Coder-7B-Vietnamese-LoRA. khoin68/Qwen2.5-Coder-7B-Vietnamese-LoRA is a LoRA adapter, not full weights: rank 32, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 28 layers (196 adapted matrices). It modifies BachDaThan/Qwen2.5-Coder-7B-Vietnamese-LoRA-GGUF at load time.

On the Hub · Downloads on Model Pulse