Full fine-tuning recipe: KTO on Mixtral 8x7B via Axolotl, targeting AWS g5.12xlarge, with data mix and eval plan.
Full fine-tuning recipe: KTO on Mixtral 8x22B via FSDP, targeting AWS g5.12xlarge, with data mix and eval plan.
Full fine-tuning recipe: KTO on Yi 1.5 34B via LLaMA-Factory, targeting AWS g5.12xlarge, with data mix and eval plan.
Full fine-tuning recipe: KTO on Llama 3.1 8B via Axolotl, targeting AWS p4d.24xlarge, with data mix and eval plan.
Full fine-tuning recipe: KTO on Llama 3.1 70B via LitGPT, targeting AWS p4d.24xlarge, with data mix and eval plan.
Full fine-tuning recipe: KTO on Mistral Nemo 12B via torchtune, targeting Lambda Labs 8xH100, with data mix and eval plan.
Full fine-tuning recipe: KTO on Qwen 2.5 7B via Unsloth, targeting Lambda Labs 8xH100, with data mix and eval plan.
Full fine-tuning recipe: KTO on Qwen 2.5-Coder 7B via OpenRLHF, targeting Lambda Labs 8xH100, with data mix and eval plan.
Full fine-tuning recipe: KTO on Gemma 2 9B via torchtune, targeting single A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: KTO on Phi-3.5-mini via Unsloth, targeting single A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: KTO on Phi-4 via OpenRLHF, targeting single H100 80GB, with data mix and eval plan.
Full fine-tuning recipe: KTO on Mixtral 8x7B via DeepSpeed, targeting single H100 80GB, with data mix and eval plan.