phh/Qwen3-0.6B-TLDR-Lora
Adapter vs Qwen/Qwen3-0.6B. phh/Qwen3-0.6B-TLDR-Lora is a LoRA adapter, not full weights: rank 8, on q_proj, v_proj in 28 layers (56 adapted matrices). It modifies Qwen/Qwen3-0.6B at load time.
Adapter vs Qwen/Qwen3-0.6B. phh/Qwen3-0.6B-TLDR-Lora is a LoRA adapter, not full weights: rank 8, on q_proj, v_proj in 28 layers (56 adapted matrices). It modifies Qwen/Qwen3-0.6B at load time.