Views
No views yet
| Parameter | Value |
|---|---|
| Base Model | unsloth/Qwen3.5-35B-A3B |
| Method | LoRA (bf16) |
| LoRA r | 16 |
| LoRA alpha | 32 |
| Target Modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Max Seq Length | 4096 |
| Batch Size | 1 |
| Gradient Accumulation | 4 |
| Epochs | 1 |
| Learning Rate | 5e-5 |
| LR Scheduler | linear |
| Weight Decay | 0.001 |
| Optimizer | adamw_8bit |
| GPU | NVIDIA H100 80GB |