Tagged fine-tuning

Build fine-tuning datasets from production logs and frontier model outputs

Fine-tune LLMs with LoRA, QLoRA and GRPO in Unsloth and export GGUF files

Build LLM and multi-agent apps with LazyLLM workflows and fine-tuning

Fine-tune public CodonFM Encodon checkpoints with LoRA or full training

Fine-tune Parakeet TDT on clinical speech with NeMo SFT and re-evaluate

Fine-tune GR00T or openpi robot policies on compatible LeRobot data

Fine-tune a KERMT molecular encoder on your labeled CSV data in a container

Plan and chain Nemotron curation, SFT, RL alignment and checkpoint conversion steps

Validate an AnomalyGenNext dataset and prepare its texture fine-tuning recipe

Fine-tune CLIP for retrieval and zero-shot tasks and export to ONNX or TensorRT

Fine-tune Cosmos-Embed1 for text-to-video search and semantic deduplication

Fine-tune Cosmos3 models on Cosmos Framework or Cosmos-RL with validated inputs

Fine-tune any Hugging Face vision, VLM or LLM model on local NVIDIA GPUs

Run and fine-tune Kumo-Anomaly diffusion detection on multivariate time series

Run and fine-tune Kumo-Forecast with DARR retrieval on multivariate time series

Fine-tune InternVideo2-CLIP for video-text retrieval and export it to TensorRT

Fine-tune AnomalyGen and generate synthetic anomaly images with quality scoring

Pretrain and fine-tune Masked Auto-Encoder backbones for vision tasks

Solve CTF challenges that involve attacking ML models, prompt injection and LoRA

Select, fine-tune and deploy ML models on Amazon SageMaker

Fine-tune and run models on Tinker with LoRA, SFT and reinforcement learning

Fine-tune DPA3 deep potential models in DeePMD-kit with the PyTorch backend

Fine-tune DPA4 deep potential checkpoints with standard or LoRA training in DeePMD-kit

Diagnose stalled reward, NaN gradients and loss issues in RL fine-tuning

Fine-tune models on Microsoft Foundry with SFT, DPO or RFT and evaluate them

Build, deploy and evaluate Microsoft Foundry agents, models and hosted agents

Choose and debug fine-tuning methods such as SFT, LoRA, DPO and GRPO by reward shape

Fine-tune large LLMs efficiently with LoRA, QLoRA and other adapter methods

Speed up LLM fine-tuning with Unsloth and cut GPU memory use with LoRA

Run LLMs and vision models on Apple Silicon with MLX Swift, including LoRA tuning

Train a custom LoRA or cloned voice on Scenario from a curated dataset

Set up QLoRA and full fine-tuning infrastructure with TRL, Axolotl and DeepSpeed

Run training, fine-tuning and inference on serverless GPUs with Modal

Fine-tune Gemma with SFT, DPO or RLHF on local hardware and export GGUF or LiteRT