Full fine-tuning recipe: IPO on Phi-4 via DeepSpeed, targeting single A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: IPO on Phi-4 via Axolotl, targeting 8x H100, with data mix and eval plan.
Full fine-tuning recipe: IPO on Gemma 2 9B via Hugging Face TRL, targeting AWS g5.12xlarge, with data mix and eval plan.
Full fine-tuning recipe: IPO on Phi-4 via FSDP, targeting AWS p4d.24xlarge, with data mix and eval plan.
Full fine-tuning recipe: IPO on Gemma 2 9B via LitGPT, targeting single H100 80GB, with data mix and eval plan.
Full fine-tuning recipe: IPO on Gemma 2 9B via Hugging Face TRL, targeting single RTX 3090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: IPO on Qwen 2.5 7B via torchtune, targeting Lambda Labs 8xH100, with data mix and eval plan.
Full fine-tuning recipe: IPO on Qwen 2.5 7B via Megatron-LM, targeting 4x A100 40GB, with data mix and eval plan.
Full fine-tuning recipe: IPO on Qwen 2.5 7B via DeepSpeed, targeting AWS g5.12xlarge, with data mix and eval plan.
Full fine-tuning recipe: IPO on Llama 3.1 70B via FSDP, targeting single A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: IPO on Llama 3.1 70B via Hugging Face TRL, targeting single RTX 4090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: KTO on Mixtral 8x7B via Axolotl, targeting AWS g5.12xlarge, with data mix and eval plan.