Tag

Gemma 4 E4B — OBLITERATED v3

Removes safety refusals from a Gemma 4 E4B–based model and publishes uncensored, locally runnable GGUF/safetensors variants while preserving all tensors and fixing prior corruption. Intended for red‑teaming and offline research; not recommended for production.

Qwen3.6-35B-A3B

Open-weight multimodal 35B Qwen3.6 model in Hugging Face Transformers format that supports image/video/text inputs and native long contexts (262,144 tokens). Emphasizes agentic coding and preserved reasoning traces (thinking), uses an MoE-backed architecture and is designed for self-hosting with vLLM/SGLang/KTransformers; requires multi-GPU resources for production.

Usenet Corpus 1980–2013

Provides deduplicated, sanitized Usenet posts (1980–2013) for language-model pretraining and linguistic research. Includes a ~103.1B-token full corpus (408M posts) with freely downloadable sample files; full corpus access requires a license and PII redaction was applied.

Leanly_AI

Clinical question-answering model for psychological support in obesity weight-management. Integrates UK Biobank population evidence to produce clinically interpretable, stigma-aware responses that help clinicians identify distress, prompt screening, and suggest appropriate referrals.

Qwen3.6-35B-A3B-DFlash

Drafts multiple tokens in parallel with a lightweight block-diffusion drafter to enable speculative decoding for faster LLM inference. Designed to pair with Qwen3.6-35B-A3B and reports up to ~2.9× throughput improvements on common benchmarks.

Qwopus-GLM-18B-Merged (Healed)

A healed 64-layer 'frankenmerge' that stacks two Qwen3.5-derived finetunes into an ~18B GGUF model for multilingual text generation, reasoning, and reliable code/frontend output. Healed with a 1000-step QLoRA to reduce layer-boundary artifacts and targeted to run on 12–16 GB GPUs.

SenseNova-U1

Unifies multimodal understanding, reasoning, and image generation in a single end-to-end architecture using the NEO-unify paradigm. Models pixels and words jointly without a separate visual encoder, and provides interleaved image–text generation, infographic editing, and GGUF/low‑VRAM inference options.

OpenAI Privacy Filter

Detects and masks personally identifiable information (PII) in text using a bidirectional token-classification model for high-throughput, on‑premises sanitization. Key traits: 1.5B parameters, 128k-token context, Apache 2.0 license, and tunable precision/recall operating points.

Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

An uncensored, fully unlocked GGUF port of Qwen 3.6‑35B‑A3B for local multimodal (text+image) inference, offering K_P 'Perfect' quant variants (Q8–Q2) and an mmproj for vision. Suited for offline research and experimentation; not for use-cases requiring safety filters.

GLM-5.1-Reasoning-1M-Cleaned

Provides a cleaned, SFT-ready collection of ~746k GLM-5.1 reasoning traces for instruction tuning and reasoning distillation. Normalizes varied chain-of-thought formats into a single conversations/input/output schema and preserves four focused subsets (main, PHD-Science, Multilingual‑STEM, Math).

SWE-Hero Trajectories (nvidia/SWE-Hero-openhands-trajectories)

Provides 34k execution-style agent trajectories (11,766 issues) for supervised fine-tuning of code-focused LLMs. Each instance includes multi-step interactions, tool-call records, and final unified diffs; generated with Qwen3-Coder and released under permissive licenses for commercial use.

Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

GGUF quantized files for a Qwen3.6-35B checkpoint fine-tuned with Claude Opus 4.6-style chain-of-thought distillation to improve reasoning. Offers multiple llama.cpp-compatible quant options (Q4/Q5/Q6/Q8) for local text-generation inference.