Tag
Explore by tags
Supervised fine-tuning dataset of instruction-style examples in English and Chinese covering generation, QA, reasoning, math and code — targeted for SFT of 10–100B-parameter LLMs. Associated with arXiv:2602.09003; first published May 21, 2026.
Fine-tuned reasoning model that speeds up structured multi-step outputs using Multi-Token Prediction (MTP) from a Qwen3.6-27B base. Produces more concise, faster generations for coding, DevOps, math, and constrained-format tasks; experimental community release for research and evaluation.
Generates audio-driven avatar videos from text, images, or audio inputs with production-grade stability (accurate lip sync, identity consistency) and an 8-step distillation inference mode for faster serving; suitable for broadcasting, virtual hosts, animation, and multi-person scenarios.
A 1.08B-parameter causal LLM engineered for on-device text generation with native long-context (131k tokens) and built-in Think/No-Think modes. It emphasizes tool-calling support, lightweight deployment formats (BF16, GGUF, MLX), and RL+OPD post-training for stronger reasoning and code generation.
A ternary-weight (~1.58-bit) 4B text-to-image diffusion transformer optimized for NVIDIA GPUs using Gemlite INT2 and HQQ; it reduces the transformer to ~1.21 GB (4.55 GB CUDA payload) and targets 1024×1024 generation with a 4-step FlowMatch-Euler sampler.
Instruction-tuned, unified Gemma 4 12B multimodal model that accepts text, image and audio inputs and generates text outputs locally. Encoder-free design reduces multimodal latency and fits on consumer devices while offering long-context support and native thinking/system-prompt features.
Provides raw newline-delimited JSON agent traces where assistant responses were generated by qwen/qwen3.7-max, captured with Teich; includes 47 JSONL files, an embedded tools schema snapshot, and conversion guidance for supervised fine‑tuning and distillation.
A 12B unified, encoder-free multimodal model that directly ingests text, images and audio and returns text; supports very long contexts (up to 256K tokens), native function-calling/thinking modes, and small-model deployment for local or on-device use.
Processes images and text to produce structured, reasoning-rich text outputs for high-throughput agentic workflows. Sparse MoE design (198B total, ~11B active per token), 256k context window and selectable reasoning levels—optimized for single-pass parsing, verification, and multi-step automation.
Generates multilingual text-to-speech with zero-shot voice cloning, token-level duration control, and inline pause markers. v1.5 improves multilingual fidelity (with language tags), cloning stability, and long-reference handling—suitable for research and production TTS pipelines.
Performs hour-scale video understanding and fine-grained temporal localization while exposing agent-style multimodal tool/code/search abilities. Built on a sparse-attention long-context architecture (DSA) and a specialized inference stack—best used in GPU-backed research or production evaluation.
Generates text with explicit chain-of-thought traces for multi-step reasoning and math-heavy tasks, emitting reasoning inside <think>...</think> blocks. Uses a Mixture-of-Experts design and 131k token context for long, verifiable workflows—best when you need inspectable reasoning.