Open-Weight Models

Krea 2 Turbo, converted to the package format libwaifu reads. The same weights drawing the same pictures; a different file layout and a narrower dtype. Either one carries the whole model: the denoiser, the language half of the Qwen3-VL text encoder, the Qwen-Image autoencoder, and the tokenizer. Nothing else has to be fetched to draw. It is distilled for eight steps at no guidance. The package says so in its suggested: block, and the thirty steps at guidance five that SDXL likes give a burnt picture here for four times the work. Measured against diffusers' Krea2Pipeline on the same weights, with every input taken off one real eight-step trajectory rather than from torch.randn: For the…

Model · Text generation

lightning-105m

AobanZ

Lightning is a small, autoregressive transformer which utilizes FlashAttention and MHA. This model is trained on a variety of books from a dataset(300 MB). This is the expanded version of Lightning-60m. Lightning utilizes FlashAttention and AdamW for performance and capability. Lightning is designed to provide quick, coherent outputs, improved with a larger size and weight. Lightning is intended to be used for research, analysis and fine-tuning, stories and other. It is not intended to be used for professional advice, real writing or any kind of heavy work as generated outputs may be incorrect. Lightning can be used directly for text generation, experimentation, and conversational…

Model

lightweight-multimodal-reading

Joshua Morales

This repository contains a working research note about Lightweight Multimodal. It organizes motivation, related work, a falsifiable hypothesis, and an evaluation plan. It is not presented as a completed paper or a release of trained models. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with notes.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they…

Model

lightweight-multimodal-study

Kyle E. Martin

This repository contains a working research note about Lightweight Multimodal. It organizes motivation, related work, a falsifiable hypothesis, and an evaluation plan. It is not presented as a completed paper or a release of trained models. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with papernotes.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they…

Model

lihua_imu_iros2026_v1

Li Hua

Public, reproducible inference for the Tartan IMU Challenge (IROS 2026). Task. Given 6-axis IMU windows (acc 3 + gyro 3, length 200) covering a motion window plus its temporal context, predict body-frame velocity (vx, vy, vz) for all four platforms (car / dog / drone / human) with a single unified model. Model. lihuaimuiros2026v1: a shared ResNet1D encoder with an FFT branch, followed by a Transformer over a triplet of consecutive windows (prev / curr / next), and a 4-expert Mixture-of-Experts head. The expert gate is a soft router driven purely by IMU-derived features — experts are learned motion regimes (general / slow / fast / agile), not platforms. A single frozen checkpoint (seed 0) is…

Model

lil-catalog

Local Inference Lab

Launch manifests for the lil launcher. Each entry is a directory holding one lil.yaml that names the repository holding the weights, optionally pins the commit the local inference lab qualified, and states the serving policy the launcher cannot read from the checkpoint itself. Checkpoint facts come from the weight repository at the resolved commit. Entries of kind: draft describe speculative-decoding drafts and are not served directly. The entry directory name is the launch name: The schema is documented in the launcher repository.

Model

ling-3.0-tiny-sft-agentic

Waylon Brown

PEFT LoRA adapter on inclusionAI/Ling-3.0-tiny (7.9B hybrid MoE, 1.3B active). Trained for coding chat and agentic SWE tool use. SFT-T has no think traces (enablethinking=False). Assistant-only labels, left-truncate to 4096 tokens. - LoRA r=16, alpha=32, dropout=0.05 on attention projections - 1000 optimizer steps (~0.52 epoch), batch 2, grad accum 4, lr 2e-4 cosine, bf16

Model

lingtai

Zesen Huang

The self-evolving Digital Scientist — a lifelong agent that grows with you and your & agent tools give you a better one-shot worker: a chat window that forgets, or a coding agent that closes with the terminal. LingTai is different — it is a Digital Scientist that lives in your project and gets better over time. It holds a question or a codebase for weeks, works with evidence and tools, records what it learns as durable knowledge and reusable skills, forms its own operating style, and delegates deep sub-problems to specialists it spawns. The work you do together becomes state the next session starts from. It is filesystem-native, not a chat window. Every agent has a home under.lingtai/; its…

Model · Image and text to text

linne-oak-1-0

Hert4

linne-oak-1.0 is a 31B decision model. Give it a state (text, a document, JSON, a conversation or an agent trajectory) and a question with a set of options, and it returns one option together with a probability for every option, in a single forward pass. It is the larger sibling of linne-fern-1.0: linne-fern is a 27B causal model that also chats, linne-oak is a dedicated decision model. - Decision Index public score 63.94, measured with the official kit (edition 0.3, all 37 public benchmarks, 140,620 requests, complete). - Reads the whole prompt at once: the full-attention layers attend in both directions over the prompt (sliding-window layers keep their native behavior), so the decision…

Model · Image classification

lite-rt_models_cadrylpro

Unicorn Who Dev

Six specialized models in 13 LiteRT files, with input/output contracts, labels, artifact hashes and CPU inference examples. The repository is public; access to its files requires manual approval on Hugging Face. Scores are specific to each model's test set and metric; they are not a common cross-task ranking. The 320 px PCB1 model is a separate compact variant of the 448 px model. See catalogue.json for exact values and source revisions. Request access on this page. After approval, authenticate and download the pinned For a binary mask or bounding boxes: Each model directory contains.tflite files, labels.txt, contract.json, format-specific metrics and CPU inference evidence. FP16 is the…

WebAssembly + WebGPU runtime binaries and the matching @litert-lm/core TypeScript SDK for running Gemma 4 (E2B, E4B, 12B, 26B-A4B, 31B) in the browser with: - Text decode with shared-KV neural Multi-Token Prediction (MTP) speculative decoding (GPUARTISAN backend, gamma 1-3, greedy token-for-token equivalence with standard decode). - Multimodal vision (SigLIP encoder on WebGPU, 70 / 140 / 280 / 560 / 1120 token budgets, zero-copy RGBA8 ImageData preprocessing, per-budget executor memory release). - Multimodal audio (Conformer encoder, streaming markers, zero-copy audio ingestion). - Streamed model loading for 2-20 GB.litertlm bundles under wasm32 (MAXIMUMMEMORY=4GB), with section filtering…