Gemma-UA-Cardio consists of two professional large language models specifically designed for the Ukrainian cardiology field. They are based on Google's Gemma and MedGemma models and have undergone two-stage fine-tuning (language adaptation and domain specialization). They can accurately provide cardiovascular medical information and answer clinical questions in Ukrainian, serving as auxiliary tools for medical professionals.

Natural Language ProcessingTransformersOther

VibeThinker-1.5B is a 1.5-billion-parameter dense language model launched by Weibo AI. It is fine-tuned based on Qwen2.5-Math-1.5B and is specifically designed for mathematical and algorithmic coding problems. Trained using the 'Spectrum to Signal Principle' framework, it outperforms larger models in multiple math competition tests. The training cost is approximately $7,800, and it supports an output of up to about 40k tokens.

Natural Language ProcessingTransformersMultiple Languages

Qwen3-32B is the latest generation of large language models in the Qwen series, with powerful reasoning, instruction-following, intelligent agent interaction, and multilingual processing capabilities. It supports over 100 languages and dialects and can seamlessly switch between thinking and non-thinking modes, providing users with a natural and smooth dialogue experience.

Natural Language ProcessingTransformers

gpt-oss-safeguard-20b is a security inference model fine-tuned based on GPT-OSS-20b, specifically designed for input-output filtering of large language models, online content annotation, and offline annotation for trust and security use cases. This model uses the Apache 2.0 license and supports custom policies and a transparent decision-making process.

Natural Language ProcessingTransformers

GPT-OSS-Safeguard-20B is a security reasoning model with 21 billion parameters built on GPT-OSS, specifically optimized for security-related text content classification and filtering tasks. This model supports custom security policies, provides a transparent reasoning process, and is suitable for security use cases such as input-output filtering of large language models and online content annotation.

Natural Language ProcessingTransformers

FineCat-NLI Large is a natural language inference model fine-tuned based on the tasksource/ModernBERT-large-nli model. It is trained on the high-quality FineCat-NLI dataset, combining the advantages of multiple excellent models and performing outstandingly in NLI tasks while maintaining the efficient characteristics of the ModernBERT architecture.

Natural Language ProcessingSentence-transformersEnglish

PokeeResearch - 7B is a 7 - billion - parameter in - depth research agent model developed by Pokee AI. It combines Reinforcement Learning from AI Feedback (RLAIF) and a powerful reasoning framework, enabling reliable, aligned, and scalable research - level reasoning in tool - enhanced large language models. It is suitable for complex multi - step research workflows.

Natural Language ProcessingTransformersEnglish

This is a sequence-to-sequence model specifically designed to compress short user prompts (≤64 tokens) and can achieve low-latency operation of less than 100 milliseconds on modern GPUs. It serves as a lightweight preprocessing stage to support high-capacity large language models.

Natural Language ProcessingTransformers

Qwen3-Next-80B-A3B-Thinking-1M-qx64n-mlx is a large language model that adopts a mixture-of-experts architecture and Deckard mixed precision quantization technology. It has 80 billion parameters and a context length of 1M tokens. This model performs excellently in science and technology reasoning and long text processing, showing a 20 - 35% improvement in cognitive benchmark tests compared to instruction models.

Natural Language ProcessingMlx

The INL architecture is a production-level neural architecture based on integral neuron dynamics, replacing traditional feed-forward network layers with iterative dynamics. It is suitable for various types of models such as large language models, vision transformers, and multi-modal models.

Natural Language ProcessingSafetensorsEnglish

dParallel is a learnable parallel decoding method for large language models that achieves fast sampling by exploiting the intrinsic parallelism of the model. This method can significantly reduce the decoding steps while maintaining the model performance, achieving 8.5 - 10.5 times acceleration in benchmarks such as GSM8K and MBPP.

Natural Language ProcessingTransformers

Bee-8B is an advanced fully open-source multimodal large language model that focuses on data quality and aims to narrow the performance gap with proprietary models. By using the high-quality Honey-Data-15M corpus and the advanced data processing pipeline HoneyPipe, it demonstrates excellent performance in complex reasoning and other aspects.

MultimodalTransformersEnglish

This is the first - generation powerful vibe - code large language model, optimized to directly generate natural language and code completion based on loosely structured 'atmosphere coding' prompts. Compared with early models, it has lower prompt engineering overhead, smoother latent space interpolation, and is easier to guide the generation of usable code.

Natural Language ProcessingTransformersEnglish

Apertus is a fully open multilingual large language model developed by Swiss AI, offering two parameter scales of 7 billion and 8 billion. This model supports over 1000 languages, uses fully compliant and open training data, and its performance can rival that of closed-source models. Apertus was pre-trained on 15T tokens and adopts a phased curriculum training method, supporting a context length of up to 65,536 tokens.

Natural Language ProcessingTransformersOther

Apertus is a fully open multilingual large language model developed by Swiss AI. It has parameter scales of 8 billion and 70 billion, supports over 1000 languages and long context processing, and only uses fully compliant open training data. Its performance can rival that of closed-source models.

Natural Language ProcessingTransformersOther

dParallel is a learnable parallel decoding method for large language models. It achieves fast sampling by exploring the intrinsic parallelism of the model, significantly reducing the decoding steps while maintaining performance, and achieving 8.5 - 10.5 times acceleration in benchmark tests such as GSM8K and MBPP.

Natural Language ProcessingTransformers

KaLM-Embedding-V2.5 is a general-purpose and lightweight embedding model. Through excellent training techniques and data, it achieves the best performance among models of the same scale and can even compete with models 3 - 26 times larger in scale. It supports multiple languages and various embedding dimension options.

Natural Language ProcessingSentence-transformersMultiple Languages

PatchFM is a basic model for univariate time series forecasting based on the Transformer architecture. It uses a block-by-block forecasting method, drawing on the training ideas of large language models to divide the time series into blocks for next-block forecasting. It supports multi-quantile output and uncertainty estimation.

Scientific ComputingSafetensors

QuestA is an innovative framework that enhances the reasoning ability of large language models through a question-enhanced approach. It integrates partial solutions during the reinforcement learning training process, significantly improving the model's performance on complex tasks such as mathematical reasoning, especially achieving optimal results on small-parameter models.

Natural Language ProcessingTransformers

VLA-Adapter is a micro vision-language-action model trained on Libero-Spatial. It adopts the Prismatic-VLM architecture and only uses Qwen2.5-0.5B as the large language model backbone. This model outperforms open-source VLA models with larger parameter scales in robot benchmarks, achieving high-performance vision-language-action understanding and execution.

MultimodalSafetensorsEnglish