Full fine-tuning recipe: DPO on Llama 3.1 70B via DeepSpeed, targeting 2x A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: DPO on Mistral Nemo 12B via Hugging Face TRL, targeting 2x A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: DPO on Qwen 2.5 7B via Megatron-LM, targeting 4x A100 40GB, with data mix and eval plan.
Full fine-tuning recipe: DPO on Qwen 2.5 32B via FSDP, targeting 4x A100 40GB, with data mix and eval plan.
Full fine-tuning recipe: DPO on Gemma 2 9B via LLaMA-Factory, targeting 8x H100, with data mix and eval plan.
Full fine-tuning recipe: DPO on Gemma 2 27B via Axolotl, targeting 8x H100, with data mix and eval plan.
Full fine-tuning recipe: DPO on Phi-4 via FSDP, targeting 8x H100, with data mix and eval plan.
Full fine-tuning recipe: DPO on DeepSeek-V3 base via LLaMA-Factory, targeting single RTX 4090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: DPO on Mixtral 8x22B via Axolotl, targeting single RTX 4090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: DPO on Yi 1.5 34B via LitGPT, targeting single RTX 3090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: DPO on Llama 3.1 8B via torchtune, targeting single RTX 3090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: DPO on Llama 3.1 70B via Unsloth, targeting single RTX 3090 (24GB), with data mix and eval plan.