DeepSeek-GRM-16B is a generative reward model based on Self-Principled Critique Tuning (SPCT), which can generate a transparent 'Principle → Critique → Score' evaluation process for query-responses and can be used in tasks such as reinforcement learning, evaluation, and data collection of large language models.

Natural Language ProcessingTransformersMultiple Languages

DeepSeek-V3.1 is a large language model that is post-trained based on DeepSeek-V3.1-Base. It has a 128K context length and supports mixed thinking modes, intelligent tool invocation, and code proxy functions. This model performs excellently in multiple benchmark tests, especially showing significant improvements in mathematical reasoning, code generation, and search agent tasks.

Natural Language ProcessingTransformersMultiple Languages

DeepSeek-V3.1 is a large language model developed by DeepSeek-AI and is an upgraded version of DeepSeek-V3. This model supports both hybrid thinking mode and non-thinking mode, and performs excellently in tool invocation, code generation, mathematical reasoning, etc., supporting a context length of 128K.

Natural Language ProcessingTransformers

This is the 4-bit quantized version of the DeepSeek-V3.1-Base model, converted using the mlx-lm tool and specifically optimized for Apple Silicon chips, providing efficient large language model inference capabilities.

Natural Language ProcessingMlx

DeepSeek-V3.1 is a large-scale language model developed by the DeepSeek team. It supports both thinking mode and non-thinking mode and performs excellently in multiple benchmark tests. It has powerful text understanding, generation, and reasoning capabilities.

Natural Language ProcessingTransformers

DeepSeek-R1 is an inference model trained through large-scale reinforcement learning. It performs excellently in mathematics, code, and reasoning tasks, and can demonstrate powerful reasoning abilities without supervised fine-tuning, including self-verification, reflection, and generating long thought chains, etc.

Natural Language ProcessingTransformersEnglish

This is the MLX format conversion version of the DeepSeek-R1-Distill-Qwen-32B model, a large language model with 32 billion parameters, specifically optimized for the MLX framework, supporting efficient text generation and dialogue tasks.

Natural Language ProcessingMlx

This is a large language model based on the DeepSeek-R1-Distill-Qwen-7B model, fine-tuned using the open-r1/OpenR1-Math-220k mathematical dataset. This model is specifically optimized for mathematical reasoning and problem-solving abilities and is trained using the TRL framework.

Natural Language ProcessingTransformers

DeepSeek-R1-0528 is an upgraded large language model launched by DeepSeek. It has significant improvements in reasoning ability and reducing hallucination rate, and its overall performance is close to that of leading models.

Natural Language ProcessingTransformers

DeepSeek-R1-Distill-Qwen-14B is an optimized large language model with a parameter scale of 14B, released by DeepSeek AI. It is distilled from the Qwen architecture and offers multiple GGUF quantization versions to improve performance.

Natural Language ProcessingGguf

This is an open-source large language model based on the DeepSeek-R1-0528-Qwen3-8B model, using Intel's AutoRound algorithm for INT4 quantization. While maintaining high performance, this model significantly reduces the model size and inference resource requirements, making it suitable for efficient inference on devices such as CPUs, Intel GPUs, or CUDA.

Natural Language ProcessingTransformers

A large language model developed by DeepSeek AI, optimized with 4-bit quantization, suitable for Apple chip devices.

Natural Language ProcessingMlx

DeepSeek-R1-0528 is a large language model that has been quantized to optimize its running efficiency on different hardware.

Natural Language ProcessingGguf

DeepSeek-R1 is a large language model focused on foundational mathematics and model reasoning capabilities.

Natural Language ProcessingTransformersEnglish

FairyR1-32B is an efficient large language model developed by Peking University DS-LAB, based on DeepSeek-R1-Distill-Qwen-32B. It achieves a balance between high performance and low-cost inference through an innovative 'distillation-fusion' process.

Natural Language ProcessingTransformersEnglish

FairyR1-32B is an efficient large language model based on DeepSeek-R1-Distill-Qwen-32B, optimized through distillation and merging processes, excelling in mathematical and programming tasks.

Natural Language ProcessingTransformersEnglish

DeepSeek - R1T - Chimera is a high-quality large language model. Through the advanced quantization scheme provided by ik_llama.cpp, it significantly reduces memory usage while maintaining performance.

Natural Language ProcessingGgufOther

DeepSeek-R1-Distill-Qwen-7B is a distilled large language model released by deepseek-ai, based on the Qwen-7B architecture, suitable for text generation tasks.

Natural Language ProcessingTransformers

GLM-4-32B-0414 is a large language model with 32 billion parameters, comparable in performance to GPT-4o and DeepSeek-V3. It supports both Chinese and English, and excels in code generation, function calling, and complex task processing.

Natural Language ProcessingGgufMultiple Languages

DeepSeek-R1 is an efficient large language model that employs Unsloth Dynamic v2.0 quantization technology to achieve outstanding accuracy.

Natural Language ProcessingGgufEnglish