AI Model2026
A 30B mixture-of-experts multilingual translation model supporting 33 languages and instruction-following translation. Offers MoE architecture, fast-thinking mode, and quantized/deployment-ready variants for production translation and subtitle tasks.
AI Model2026
A family of multilingual translation models optimized for real-world, instruction-following translation across 33 languages. The 1.8B model targets on-device use with extreme quantization (≈440 MB via AngelSlim), while 7B/30B variants trade size for higher accuracy.
AI Model2026
7B multilingual translation model optimized for instruction-following and low-latency deployment across 33 languages; provides quantized/FP8/GGUF builds and integrations (vLLM, llama.cpp) for server and on-device inference.
AI Dataset2026
OCR-extracted Vietnamese annual financial reports (2015–2025) from 18,231 filings across 1,491 tickers — plain-text OCR outputs for document-QA, information extraction, VLM/RAG development. Contains only TXT OCR files; CC BY-NC 4.0 license.
AI Dataset2026
Multilingual benchmark for evaluating LLMs' industrial domain knowledge via 2,049 expert-curated QA pairs spanning 10 product verticals and four languages, with each item grounded to industry or national standards and an LLM-as-judge evaluation pipeline.
AI Model2026
Converts video inputs into text outputs — supports captioning, temporal grounding, and video-text-to-text queries using a Qwen-3.5-2B finetuned multimodal backbone. Suited for prototyping video understanding and caption-generation pipelines.
AI Model2026
Early pretraining checkpoint of a compact multilingual causal LM aimed at low-memory deployment and Indic language support. Explores a Shared KV cache mode that can cut KV-cache memory by ~50% for inference; results are provisional (not a final, fully trained model).
AI Model2026
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.
Measures how well LLMs and agent-driven workflows prepare supervised training data end-to-end by jointly benchmarking data construction and data-quality evaluation across six domains, using a downstream-grounded protocol and new metrics.
AI Dataset2026
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.
AI Dataset2026
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.
AI Dataset2026
RL training dataset for long-context language-model fine-tuning with ~23K samples and nine reward types, provided in Parquet with bilingual ground-truth and reward metadata for direct RL/bench evaluation.