Full fine-tuning recipe: IPO on Mistral Nemo 12B via torchtune, targeting AWS g5.12xlarge, with data mix and eval plan.
Full fine-tuning recipe: IPO on Qwen 2.5 32B via Unsloth, targeting AWS p4d.24xlarge, with data mix and eval plan.
Full fine-tuning recipe: IPO on Qwen 2.5-Coder 7B via OpenRLHF, targeting AWS p4d.24xlarge, with data mix and eval plan.
Full fine-tuning recipe: IPO on Gemma 2 27B via DeepSpeed, targeting Lambda Labs 8xH100, with data mix and eval plan.
Full fine-tuning recipe: IPO on Phi-3.5-mini via Unsloth, targeting Lambda Labs 8xH100, with data mix and eval plan.
Full fine-tuning recipe: IPO on DeepSeek-V3 base via OpenRLHF, targeting Lambda Labs 8xH100, with data mix and eval plan.
Full fine-tuning recipe: IPO on Mixtral 8x7B via DeepSpeed, targeting single A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: IPO on Yi 1.5 34B via Hugging Face TRL, targeting single A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: IPO on Llama 3.3 70B via Megatron-LM, targeting single H100 80GB, with data mix and eval plan.
Full fine-tuning recipe: IPO on Llama 3.1 8B via FSDP, targeting single H100 80GB, with data mix and eval plan.
Full fine-tuning recipe: IPO on Mistral Small 3 via LLaMA-Factory, targeting single H100 80GB, with data mix and eval plan.
Full fine-tuning recipe: IPO on Mistral Nemo 12B via Megatron-LM, targeting 2x A100 80GB, with data mix and eval plan.