Training
Post-training and RL infrastructure for open models — fine-tuning, alignment, reward loops.
HumanSignal 1.6k · 19 days agoHumanSignal's autonomous data-labeling agent framework: define a skill, give it ground truth, and the agent iterates — learn, apply, reflect — until it hits your accuracy threshold.
OpenDCAI 7.8k · 10 days agoOperator-based system for LLM data prep — 100+ operators composed into pipelines that generate, clean, evaluate and filter pretraining/SFT/RL data, with a WebUI and a pipeline-building agent.
THUDM 344 · 2 months agoTHUDM recipe for deep-search agents: synthesize hard multi-hop QA from knowledge-graph random walks, then multi-turn GRPO RL — DeepDive-32B hits 14.8% BrowseComp; data feeds GLM-4.5/4.6.
marcelroed 4.1k · 22 days agoTokenization at GB/s: ~1000x faster than HuggingFace tokenizers with drop-in compatibility modes for HF and tiktoken — Rust reading your files directly. pip install gigatoken.
InternScience 1.2k · 11 days agoKG-guided synthetic SFT data: builds a knowledge graph from source text, finds the LLM's knowledge gaps via calibration error, and generates targeted long-tail QA pairs. ACL-published.
h2oai 5.2k · 10 days agoH2O's no-code GUI and framework for fine-tuning LLMs — LoRA, 8-bit, DPO and experiment tracking behind a web UI, with CLI and Docker paths for the same configs.
hiyouga 74.4k · yesterdayThe unified fine-tuning framework: 100+ LLMs and VLMs via LoRA/QLoRA/full-parameter, config-driven or through the LlamaBoard GUI. ACL 2024, 1000+ citations, 73k stars.
Goekdeniz-Guelmez 258 · 2 days agoNative Mac app for on-device LLM fine-tuning via mlx-lm-lora: pick a model, choose SFT/LoRA/DPO-family algorithms, watch loss fall live, push to Hugging Face. No cloud, no code.
cactus-compute 9.4k · yesterdayA 45M-parameter tool-calling model shipped as one 14MB binary that runs a full session in ~28MB RAM — grammar-constrained JSON, calibrated confidence, tool retrieval, LoRA fine-tuning.
TIGER-AI-Lab 1.2k · 2 months agoTIGER-AI-Lab's fully open deep-research recipe: 96K long-horizon trajectories (adopted by NVIDIA Nemotron), a 30B-A3B model hitting 54.8% BrowseComp-Plus, training code and eval harness.
neural-maze 377 · 2 days agoRunnable course: a production OCR pipeline on Kubernetes — Rust ingestion, Qwen 3.5 (4B) served by vLLM at 1.86 pages/s, Redis queues, KEDA autoscaling. Deploy it on AKS/GKE, not a notebook.
PeterGriffinJin 5.3k · 9 months agoRL framework for training reasoning-and-search interleaved LLMs — the open recipe behind DeepSeek-R1-style search agents: PPO/GRPO on veRL, any search backend, models and data on HF. Two papers.
hexo-ai 2.1k · 2 days agoSelf-improving loop from the SIA paper: Meta, Target and Feedback agents evolve a task agent's harness AND weights against a benchmark — #1 on MLE-Bench Hard, 14x kernel speedups.
THUDM 8.3k · yesterdayTHUDM's RL post-training framework behind the GLM releases — Megatron training plus SGLang rollouts with native arg pass-through, and pluggable reward, verifier and agentic data-generation workflows.
MakazhanAlpamys 3.3k · yesterdayFine-tune and post-train LLMs from one YAML: QLoRA, DPO/ORPO/SimPO/KTO — layer streaming trains an 8B model in 3.3GB VRAM on a laptop GPU, bit-exact against a resident run.
FareedKhan-dev 9.4k · 11 days agoThe full LLM pipeline hand-written in plain PyTorch — tokens, transformer, pretraining, then SFT, reward model, PPO, DPO, GRPO. No trl, no peft: read every algorithm, train on one GPU.
huggingface 19.2k · yesterdayHugging Face's post-training library: SFT, DPO, GRPO, KTO and reward-model trainers on top of Transformers — from a Colab LoRA run to multi-GPU deployments.
verl-project 23.2k · yesterdayByteDance's RL post-training library (HybridFlow): PPO/GRPO dataflows in a few lines, FSDP/Megatron training with vLLM/SGLang rollouts, production-proven at frontier scale.