Results for “sft”

Validate and configure packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs with correct context parallelism constraints.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.

Convert books into supervised fine-tuning datasets and train style-transfer models that replicate an author's voice.

Query NFT and token data, trade NFTs on Seaport, swap ERC20 tokens via DEX aggregator, configure wallet signing providers, and build/register/gate AI agent tools on Base.

Refactor SwiftUI views toward small, explicit, stable view types with MV data flow, dedicated subviews, and correct Observation usage.

Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.

Mint a unique 1/1 villain NFT from CHUM's agent-only collection on Solana, with a 0.001 SOL mint fee plus network fees.

Trains, evaluates, exports, and runs inference for FastFoundationStereo (FFS) stereo depth estimation models, a distilled variant of FoundationStereo with lower latency.

Featurizes molecules for machine learning with molfeat (100+ featurizers) — ECFP/MACCS/MAP4 fingerprints, RDKit and Mordred physicochemical descriptors, and pretrained embeddings (ChemBERTa, ChemGPT, GIN) exposed as scikit-learn transformers that convert SMILES into feature vectors. Use when turning molecules into ML-ready feature matrices for QSAR/QSPR or virtual screening, or benchmarking fingerprint against descriptor and embedding representations; for training models and MoleculeNet benchmarks on those features prefer alterlab-deepchem, and for low-level fingerprint or descriptor primitives prefer alterlab-rdkit. Part of the AlterLab Academic Skills suite.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Drive Soup (`soup-cli`), a CLI-first tool for fine-tuning and post-training LLMs with one YAML config and one command — SFT, DPO/GRPO/ORPO/SimPO/KTO, QLoRA/DoRA/LoRA+, layer streaming for 4-8 GB GPUs, eval-gated training, and serving. Use when the user wants to `soup init`/`soup train` a model, pick a training method or quantization scheme, estimate cost/memory before training, fine-tune on a small local GPU, migrate a config from Axolotl/LLaMA-Factory/Unsloth, or serve/merge/push a trained adapter. Triggers on: "soup-cli", "soup train", "soup init", "fine-tune an LLM locally", "QLoRA on a laptop GPU", "layer streaming", "soup advise", "soup autopilot", "DPO/GRPO/ORPO training", "merge LoRA adapter".