Full fine-tuning recipe: QLoRA (4-bit) on Mistral Nemo 12B via Hugging Face TRL, targeting single H100 80GB, with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Qwen 2.5 32B via Megatron-LM, targeting 2x A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Qwen 2.5-Coder 7B via FSDP, targeting 2x A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Gemma 2 9B via LLaMA-Factory, targeting 2x A100 80GB, with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Phi-3.5-mini via Axolotl, targeting 4x A100 40GB, with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Phi-4 via LitGPT, targeting 4x A100 40GB, with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Mixtral 8x7B via LLaMA-Factory, targeting 8x H100, with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Mixtral 8x22B via Axolotl, targeting 8x H100, with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Llama 3.3 70B via LitGPT, targeting 8x H100, with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Llama 3.1 8B via torchtune, targeting single RTX 4090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Mistral Small 3 via Unsloth, targeting single RTX 4090 (24GB), with data mix and eval plan.
Full fine-tuning recipe: QLoRA (4-bit) on Mistral Nemo 12B via OpenRLHF, targeting single RTX 3090 (24GB), with data mix and eval plan.