Full fine-tuning recipe: SFT (supervised fine-tuning) on Qwen 2.5 7B via Hugging Face TRL, targeting 2x A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: LoRA on Qwen 2.5 32B via Megatron-LM, targeting 2x A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: LoRA on Gemma 2 9B via FSDP, targeting 4x A100 40GB, with data mix and eval plan.
Full fine-tuning recipe: LoRA on Gemma 2 27B via LLaMA-Factory, targeting 4x A100 40GB, with data mix and eval plan.
Full fine-tuning recipe: LoRA on Phi-3.5-mini via Megatron-LM, targeting 8x H100, with data mix and eval plan.
Full fine-tuning recipe: LoRA on DeepSeek-V3 base via FSDP, targeting 8x H100, with data mix and eval plan.
Full fine-tuning recipe: LoRA on Mixtral 8x7B via LLaMA-Factory, targeting 8x H100, with data mix and eval plan.
Full fine-tuning recipe: LoRA on Yi 1.5 34B via Axolotl, targeting single RTX 4090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: LoRA on Llama 3.3 70B via LitGPT, targeting single RTX 4090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: LoRA on Llama 3.1 70B via torchtune, targeting single RTX 3090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: LoRA on Mistral Small 3 via Axolotl, targeting single RTX 3090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: LoRA on Qwen 2.5 7B via LitGPT, targeting single RTX 3090 (24GB), with data mix and eval plan.