AI Dataset2026
Contains 4,006 newline-delimited JSONL agent-session traces recording assistant responses and tool calls from deepseek/deepseek-v4-pro — includes a training-ready tools schema snapshot and helpers for conversion to SFT/distillation workflows.
AI Model2026
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.
Learns fine-grained preferences over sub-trajectories to identify and penalize redundant steps in long chain-of-thoughts, letting models "fold" reasoning chains into concise paths; reports ~56% token reduction on DeepSeek-R1-Distill-Qwen-7B while keeping accuracy.
AI Dataset2026
Pairs OCR-extracted annual-report text with ground-truth financial KPI values to benchmark LLM/table-QA and needle-in-a-haystack extraction tasks. Includes Markdown OCR (.mmd), page images for eval, and 31 KPI columns across multiple years—suited for KPI extraction, retrieval, and robustness testing.
AI Agent Papers2026
Synthesizes shortcut-resistant search tasks to train deep search agents by controlling four shortcut risks across entity selection, evidence-graph construction, question formulation, and adversarial refinement. Produces training trajectories with longer pre-answer search and fewer shortcut patterns; code will be released on GitHub.
AI Model2026
Provides a large language model optimized for long-horizon agentic tasks and end-to-end coding workflows — with a stable 1,000,000-token context, IndexShare sparse-attention and multi-level thinking-effort modes. MIT-licensed and designed for deployments that need sustained long-context reasoning and coding.
AI Model2026
Performs one-shot, long-horizon OCR and document parsing by using Reference Sliding Window Attention (R-SWA) to keep the decoder KV cache constant, enabling single-pass multi-page transcription; code, model weights and an accompanying arXiv report are provided.
AI Model2026
Mixture-of-Experts LLM designed for million-token contexts, combining hybrid compressed attention, FP4/FP8 quantization-aware training for MoE experts, and multi-mode 'thinking' (Non-think/Think High/Think Max); includes a speculative-decoding extension for faster inference.
AI Model2026
A Hugging Face model checkpoint that attaches a speculative decoding module to DeepSeek-V4-Flash, enabling million-token context handling with MoE architecture, FP4/FP8 mixed precision, and long-context inference optimizations.
AI Dataset2026
Provides 16M+ instruction–response samples and ~81 GB (7,090 compressed GitHub repos) distilled from 68 open-source sources, organized into 8 categories for SFT, coding agents and reasoning research. Model-generated content; released as a curated MIT-licensed collection.
AI Model2026
GGUF-format quantized release of DeepSeek‑V4‑Flash for local inference — compatible with llama.cpp and Unsloth runtimes, with guidance for FP4/FP8 mixed precision and Q4/Q8 quantization; tuned for million-token long-context usage.
AI Dataset2026
Provides ~5M model-generated reasoning chains (within 5k sequence length) with structured fields for supervised fine-tuning, reasoning distillation, and instruction tuning. Includes separate fields for prompt, reasoning trace, final answer and a ChatML view; streaming access recommended for large-scale use.