Fathom-DeepResearch is an intelligent deep research system composed of two specialized 4B parameter models: Fathom-Search-4B is optimized for long-term evidence search, and Fathom-Synthesizer-4B is used for open-ended synthesis and report generation. This system has achieved state-of-the-art performance in multiple search-intensive benchmark tests and has outperformed multiple closed-source deep research agents on the open-ended synthesis benchmark.

Natural Language ProcessingTransformers

NVIDIA-Nemotron-Nano-9B-v2 is a large language model newly trained by NVIDIA, a unified model designed for both inference and non-inference tasks. It adopts the Mamba2 - Transformer hybrid architecture, supports multiple languages, and has controllable inference capabilities. Users can control the display of the model's inference process through system prompts. The model performs excellently in multiple benchmark tests and is commercially available.

Natural Language ProcessingTransformersMultiple Languages

MMIE is an evaluation benchmark specifically designed for large vision-language models, featuring an automated scoring system to test multimodal interleaved comprehension capabilities.

MultimodalSafetensorsEnglish

Flames Scorer is a high-adversarial benchmark testing platform scoring system specifically designed for evaluating value alignment in Chinese large language models

Natural Language ProcessingTransformersChinese

Phi 2 - llamafile is the llamafile format version of the Microsoft Phi-2 model, offering multiple quantization methods and supporting operation on various operating systems. This model has 2.7 billion parameters and performs excellently in benchmark tests such as common sense, language understanding, and logical reasoning, approaching the current optimal level.

Natural Language ProcessingTransformersMultiple Languages