Luna-A0-12B
2nd run of an experiment to give the "assistant" a better voice. Functional but significantly degrades writing quality and aligns the model closer to self-censorship.
Training Configuration
| Parameter | Value |
|---|---|
| Training Mode | ORPO |
| Base Model | schneewolflabs/A0i-12B |
| Learning Rate | 5e-05 |
| Epochs | 1 |
| Batch Size | 1 |
| Gradient Accumulation | 4 |
| Effective Batch Size | 4 |
| Max Sequence Length | 2048 |
| Optimizer | paged_adamw_8bit |
| LR Scheduler | cosine |
| Warmup Ratio | 0.05 |
| Weight Decay | 0.01 |
| Max Grad Norm | 0.25 |
| Seed | 42 |
| ORPO Beta | 0.1 |
| Max Prompt Length | 1024 |
| LoRA Rank (r) | 16 |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| Target Modules | up_proj, down_proj, gate_proj, k_proj, q_proj, v_proj, o_proj |
| Quantization | 4-bit (NF4) |
| GPU | NVIDIA RTX A6000 |
- Downloads last month
- 23