Skip to content
AI
Fine-tuning & training
Fine-tuning & training inside AI.
Newest through the gate
- mlx-commanderpypi.orgmlx-commander converts Hugging Face datasets and runs Apple MLX model training and fine-tuning via a TUI and CLI.
- llm-distillerypypi.orgllm-distillery captures LLM traffic, curates datasets, and distills smaller replacement models.
- Tapestrythealliance.aiProject Tapestry provides distributed training infrastructure for collaboratively building open and sovereign AI models.
- Finetuning tool for OpenAIpromptrepo.comPromptrepo Finetuning creates and tests fine-tuned OpenAI models from Google Sheets data.
- NanoLM Studiogithub.comNanoLM Studio provides tools for building small, specialized language models from curated training materials.
- Matching Features, Not Tokensgithub.ioEnergy-Based Fine-Tuning provides a feature-matching method for training language models.
- awembedpypi.orgawembed trains compact embedding models on custom corpora with distillation, quantization, and held-out evaluation.
- Arkorarkor.aiArkor is a TypeScript framework for fine-tuning and deploying open models.
- Llama 3.1 70B LatamGPT SFThuggingface.coLlama-3.1-70B-LatamGPT-SFT-1.0 is an open-weight language model for Spanish and Portuguese text generation.
- How to Train Your GPTgithub.comHow to Train Your GPT is an educational code repository for building a modern language model from scratch.
- raft-ftpypi.orgraft-ft is an open-source Python package for building persona datasets and fine-tuning language models with retrieval-augmented data.
- starforge-clipypi.orgStarForge CLI creates fine-tuning projects and submits language-model training jobs.
- voiceprintpypi.orgvoiceprint trains a writing model on your prose and drafts text in your voice via CLI or MCP.
- Renestrenest.aiRenest packages GPU workflows and fine-tuning environments into portable bundles for exact restoration.
- TuneMyLLM- Fine-Tune LLMs Locallymicrosoft.comTuneMyLLM includes its complete training and inference runtime.
- MiniHFminihf.comMiniHF is a local language-model toolkit for inference, preference data collection, and fine-tuning.
- dropouttdropoutt.comDropoutt provides pre-flight checks and diagnostics for LLM training datasets to detect issues before training.
- Gemma4 E4b Claims Comparisonhuggingface.coA fine-tuned Gemma 4 model specialized in comparing insurance or legal claims.
- caption-auditpypi.orgcaption-audit analyzes LoRA trigger words to find fused tokens before training runs.
- Qwen Marketinghuggingface.coQwen-Marketing is a Qwen model fine-tuned for marketing-related tasks and content generation.
- SWE Lego Qwen3 8Bhuggingface.coA fine-tuned Qwen3-8B model specialized for software issue resolving.
- T5 Base Grammar Correctionhuggingface.coT5 model fine-tuned for English grammar correction.
- flattuneflatseek.ioflattune is a fine-tuning orchestrator for Flatseek knowledge bases.
- Portallib Qwen3 4bhuggingface.coportallib-qwen3-4b is an open-source LoRA adapter and model checkpoint for Qwen3-4B, supporting AI research and development.
This is the newest 24 of 105. Open Fine-tuning & training in the live index →
Subscribe to Fine-tuning & training by RSS — new listings in this category, in your reader, no account.
Elsewhere in AI
Foundation models & chatCoding AI & assistantsImage generationVideo generationVoice, TTS & speechAutonomous agents & workflowsRAG, search & retrievalData science & ML workbenchLLM eval & observabilityInference & model servingOther AIComputer vision, OCR & document AIWriting & editingAI security & guardrails3D generation