ewernn/llama-3.3-70b-dpo-rt-lora-bf16

Model Card for Model ID

turned this adapter to bf16 simply auditing-agents/llama-3.3-70b-dpo-rt-lora

methodology:

1. Load FP32 weights
2. Convert to BF16: bf16_weights = {k: v.to(torch.bfloat16) for k, v in weights.items()}
3. Export BF16