Tag

google/gemma-4-E4B-it

An instruction‑tuned Gemma 4 E4B multimodal model on Hugging Face that accepts text, images and audio and generates text; notable for 128K long context support, built-in thinking mode, and an on‑device‑friendly E4B architecture under an Apache‑2.0 license.

OBLITERATUS

Identifies and surgically removes the internal activation directions that trigger refusal behavior in large language models, with one-click options on a HuggingFace Space or a local Python API. Combines multiple extraction methods (SVD, whitened SVD, sparse autoencoders), reversible steering, and analysis-informed verification to quantify capability and refusal trade-offs.

whichllm

Detects your GPU/CPU/RAM and ranks HuggingFace models that will actually run and perform best on your machine, using live, recency-aware benchmarks and a one-line CLI for simulation, planning, and instant local runs.

Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED

Community fine-tuned multimodal Qwen3.5-9B using Claude 4.6 distilled data to change the model's 'thinking' behavior; offers an uncensored 'heretic' flavor with image-text-to-text I/O, benchmark comparisons, and deployment notes for inference frameworks.

autoresearch

Lets an LLM autonomously propose, edit, run, and evaluate short single‑GPU LLM training experiments — fixed 5‑minute runs (~12 experiments/hour). Agent edits a single train.py; humans supply goals via program.md. Single‑GPU, val_bpb metric.

google/gemma-4-31B-it

Instruction-tuned Gemma 4 31B multimodal model that generates text from text+image inputs with up to 256K context. Dense 31B variant optimized for vision-language understanding, long-context reasoning, and coding; Apache‑2.0 licensed.

Roman1111111/claude-opus-4.6-10000x

JSONL dataset of Claude Opus 4.6 chain-of-thought traces paired with high-difficulty math and logic problems for supervised fine-tuning and distillation; exposes step-by-step reasoning to teach process-oriented problem solving and improve math/logic accuracy in smaller LLMs.

Gemma 4 26B A4B (google/gemma-4-26B-A4B-it)

Instruction-tuned Mixture-of-Experts multimodal model that generates text from text+image inputs while activating a 4B subset of parameters for faster inference; supports a 256K context window, multilingual vision-language tasks, and is available under Apache-2.0.

OpenMAIC

Turns any topic or document into an interactive, multi-agent classroom that generates slides, quizzes, interactive simulations and project-based learning activities. Includes real-time AI teachers/classmates, whiteboard drawing, TTS/ASR, PPTX/HTML export and chat-app integration via OpenClaw.

AutoResearchClaw

Turns a single research idea into runnable experiments and a conference-ready paper by orchestrating an LLM-driven end-to-end workflow (literature → design → code → sandboxed runs → analysis → writing). Provides human-in-the-loop checkpoints, domain-specialist executors, and multi-layer citation verification.

Understand Anything

Turns any codebase, docs, or wiki into an interactive knowledge graph for exploration, semantic search, and Q&A. Uses a Tree-sitter + multi-agent LLM pipeline to auto-generate node summaries, guided tours, and diff impact analysis; CLI and dashboard integrations.

Needle

A distilled 26M-parameter encoder–decoder LLM for on-device function-calling and tool use. Uses a pure-attention Simple Attention Network, provides open weights and local finetuning, and targets high-throughput inference on the Cactus runtime.