New: SLM-10M leads the Open SLM Leaderboard <10M tier — explore on HuggingFace →

Open-source deep learning,
built in public.

Compact models. Efficient architectures. Open evaluation tools.
An R&D collective — not a company, not incorporated.

What we research

Liodon is an independent, self-funded applied research lab working on the frontier of open-source foundation model research.

Models & Architecture

Small Language Models

Architectural efficiency via Transformer variants, sparse attention, quantization, and knowledge distillation — targeting models that run on constrained hardware.

  • SLM-10M — tops Open SLM Leaderboard <10M tier
  • whisper-large-v3-te — Telugu ASR fine-tune
  • GGUF variants of Gemma 4 & Qwen
  • slm-bench evaluation dataset

Python Libraries

Research Tools & Libraries

Purpose-built Python packages for the deep learning researcher — from loss functions and LLM evaluation to agentic primitives and citation auditing.

  • JuryEval — LLM-as-Judge evaluation framework
  • TorchCriterion — modular loss functions
  • TorchAgentic — agentic AI primitives
  • CitationHunter, PromptGrad, NanoNLP & more

Triton Kernels · Featured

TorchEmbed

Fused Triton kernels for RoPE and embedding operations — 4–7× faster than pure PyTorch and ~2× faster than torch.compile. Used by DeepSpeed and Microsoft.

  • RoPE fused forward & backward kernels
  • 4–7× faster than pure PyTorch
  • ~2× faster than torch.compile
  • Used by DeepSpeed & Microsoft
TorchEmbed Benchmarks

Triton-fused performance

Measured on NVIDIA GB10 (float16). The fused kernel reads and writes each element exactly once — no intermediate allocations.

Forward Pass Latency

RoPE forward pass latency benchmark

Speedup vs PyTorch & torch.compile

RoPE benchmark speedup bars
4–7×
faster than PyTorch
~2×
faster than torch.compile
5.09×
peak speedup (seq 4096)

82+

Models, Datasets & Repos

100%

Open Source (MIT / Apache 2.0)

46,000+

Downloads on HuggingFace

TorchEmbed · used by

Microsoft DeepSpeed

Featured Projects

Practical tools for the research community — all open source, all on GitHub.

Language Model

SLM-10M

10M parameter SLM leading the Open SLM Leaderboard under 10M tier. Efficient, quantizable, and freely available on HuggingFace.

Evaluation Library

JuryEval

LLM-as-Judge evaluation with statistical significance testing. Go beyond single-judge prompts with multi-judge consensus.

Research Tool

CitationHunter

Audits research papers for missing or weak citations. Built for researchers who need thorough literature grounding.

From the blog

Research notes, model releases, and open-source updates.

Ready to explore the research?

Liodon AI is not a company — just open-source research built in the open. Star a repo, open an issue, or just read the code.