Tag
Explore by tags
A GGUF-format 9B model derived from Qwen3.5, fine-tuned for agentic coding, tool-calling, reasoning and vision-capable multimodal prompts. Optimized for local 8‑bit inference on 16GB-class machines; community experimental release for research use.
Research-focused text-to-image foundation model that prioritizes training efficiency: a 3.8B-parameter architecture trained on an 800M image-text corpus with mixed-resolution learning, FLUX.2 VAE, RL tuning, and a distilled 4-step Lens-Turbo for fast high-resolution generation.
A 4-step distilled variant of Microsoft's Lens foundational text-to-image model for fast, high-resolution image synthesis. Optimized for mixed-resolution inference up to 1440×1440, GPT-OSS text features and FLUX.2 latents, intended for low-latency prototyping and research under an MIT license.
Reasoning-enhanced 27B dense LLM fine-tuned from Qwen3.6-27B and released in GGUF format for image-text-to-text and long-context reasoning. Augmented with Trace Inversion reconstructed chains, three-stage SFT curriculum and MTP/vision support; community research release.
Provides a 1-billion-parameter English pretrained language-model checkpoint that uses a dual-timescale Hierarchical Reasoning Model to increase effective compute depth. It's a PrefixLM pre-alignment checkpoint with composite-prefix modes for chain-of-thought style outputs; not instruction-tuned and requires downstream SFT/RL for assistant use.
W4A4-quantized build of a 25B-parameter multimodal LLM that produces text from image+text inputs and supports conversational tool use. Trades very small quality differences for much lower GPU memory and latency so inference can run on smaller accelerators (vLLM support).
Generates minute-scale, 720p videos from a single image using a 2.6B image-to-video diffusion transformer with precise 6‑DoF camera control and an optional LTX‑2 refiner; designed for long-context, memory-efficient modeling but requires large refiner checkpoints (~41 GB).
A GGUF-format 9B LLM fine-tuned for code generation and agentic tool-calling that uses Multi-Token Prediction (MTP) and draft heads to increase throughput and long-range planning. Intended for local inference and research/experimental coding workflows; Apache‑2.0 license.
Dataset of 5,000 reconstructed chain-of-thought samples produced by trace‑inversion from Claude‑opus‑4.7 summaries — packaged for SFT/DPO fine‑tuning. Key features: reconstructed CoT traces, multilingual prompts, gzip .jsonl format. Best used for reasoning distillation and model-level supervision; synthetic traces may need extra verification.
Provides 9,000 reconstructed chain-of-thought (CoT) SFT examples produced by trace inversion from Claude Opus 4.6 outputs for fine-tuning reasoning-capable LLMs. Multilingual, packaged as .jsonl.gz and SFT/DPO-ready; verify numeric/code cases before training.
Provides a locally runnable 26.9B Qwen3.6 checkpoint that surgically reduces refusal behavior in weight space while preserving capability; ships bfloat16 safetensors and a GGUF quant ladder for local runtimes and red-team evaluation.
Converts long-form multi-speaker audio/video into a compact, speaker-aware transcript with timestamps and anonymous speaker labels in one pass. Combines ASR and diarization in a single model, supports custom prompts/hotwords, and targets meetings, podcasts, interviews and long recordings.