Chronos-2 is a time series foundation model with 120 million parameters, supporting zero-shot prediction. It supports univariate, multivariate, and covariate-aware tasks within a single architecture, achieving state-of-the-art accuracy in zero-shot prediction across multiple benchmarks, and has extremely high inference efficiency.

Scientific ComputingSafetensors

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

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

Qwen3-4B-I-1509 is a dedicated model fine-tuned based on the Qwen3-4B-Instruct-2507 base model, focusing on tool usage and function call generation tasks. This model is trained using a reinforcement learning method with multi-signal rewards and demonstrates good performance in multiple evaluation benchmarks.

Natural Language ProcessingTransformersEnglish

OpenReasoning-Nemotron-7B is a large language model based on Qwen2.5-7B-Instruct, designed for mathematical, coding, and scientific solution reasoning. This model performs excellently in multiple reasoning benchmarks, supports the GenSelect mode to improve performance, and offers multiple scale options.

Natural Language ProcessingTransformersMultiple Languages

Llama-3.1-70B-Instruct-RM-RB2 is one of the 7 reward models released by the Allen Institute for Artificial Intelligence, used to develop benchmarks and conduct correlation analysis with downstream PPO/Best-of-N performance.

Natural Language ProcessingTransformersEnglish

QwenLong-L1 is a long-context reasoning model trained with reinforcement learning, demonstrating excellent performance across seven long-context document QA benchmarks.

Natural Language ProcessingTransformers

An improved vision-language model based on Qwen2.5-VL-72B-Instruct, excelling in multiple visual reasoning benchmarks

MultimodalGgufEnglish

An improved multimodal vision-language model based on Qwen2.5-VL-72B-Instruct, excelling in multiple visual reasoning benchmarks

MultimodalGgufEnglish

A vision-language model optimized based on Qwen2.5-VL-72B-Instruct, excelling in multiple visual reasoning benchmarks

MultimodalGgufEnglish

A 32-billion-parameter dense language model focused on enhancing reasoning capabilities, built upon Qwen 2.5-32B-Base, demonstrating performance comparable to larger MoE models in reasoning benchmarks.

Natural Language ProcessingTransformers

A medical reasoning model fine-tuned based on Qwen/Qwen2.5-7B-Instruct, excelling in multiple medical QA benchmarks

Natural Language ProcessingTransformers

OpenMath-Nemotron-32B is a mathematical reasoning model created by fine-tuning Qwen2.5-32B on the OpenMathReasoning dataset, achieving state-of-the-art results on multiple mathematical benchmarks.

Natural Language ProcessingTransformersEnglish

OpenMath-Nemotron-14B is a mathematical reasoning model fine-tuned on the OpenMathReasoning dataset based on Qwen2.5-14B, achieving state-of-the-art results on multiple mathematical benchmarks.

Natural Language ProcessingTransformersEnglish

OpenMath-Nemotron-1.5B is a mathematical reasoning model fine-tuned on the OpenMathReasoning dataset based on Qwen2.5-Math-1.5B, achieving state-of-the-art results on multiple mathematical benchmarks.

Natural Language ProcessingTransformersEnglish

OpenMath-Nemotron-7B is a mathematical reasoning model fine-tuned on the OpenMathReasoning dataset based on Qwen2.5-Math-7B, achieving state-of-the-art results on multiple mathematical benchmarks.

Natural Language ProcessingTransformersEnglish

OpenMath2-Llama3.1-8B is a math-specialized model fine-tuned from the Llama3.1-8B-Base model using the OpenMathInstruct-2 dataset, demonstrating excellent performance across multiple mathematical benchmarks.

Natural Language ProcessingTransformersEnglish

Light-R1-7B-DS is an open-source 7B mathematical model fine-tuned based on DeepSeek-R1-Distill-Qwen-7B, demonstrating excellent performance on benchmarks such as AIME24 and AIME25.

Natural Language ProcessingTransformers

The Meta Llama 3.1 series is a collection of multilingual large language models (LLMs), including pre-trained and instruction-tuned generative models in 8B, 70B, and 405B sizes. The 8B version is optimized for multilingual dialogue use cases and excels in common benchmarks.

Natural Language ProcessingGgufMultiple Languages

HyperCLOVAX-SEED-Text-Instruct-1.5B is a large language model with 1.5 billion parameters developed by NAVER. It is specifically optimized for Korean language understanding and generation tasks and performs excellently in benchmarks related to the Korean language and culture. It supports a context length of up to 16k tokens.

Natural Language ProcessingTransformers