NVIDIA DeepSeek-R1-0528-FP4 v2 is a quantized version of the DeepSeek R1 0528 model. It adopts an optimized Transformer architecture and is an autoregressive language model. Through FP4 quantization optimization, it reduces the disk size and GPU memory requirements while maintaining high inference efficiency.

Natural Language ProcessingSafetensors

This is a language model specifically optimized for the Indonesian legal field. It is fine-tuned on the Indonesian legal Q&A dataset using the GRPO method based on DeepSeek-R1-0528-Qwen3-8B, focusing on improving legal reasoning and structured thinking abilities.

Natural Language ProcessingTransformers

This model is a fine-tuned version based on DeepSeek-R1-0528-Qwen3-8B, trained using TRL and GRPO methods, focusing on improving mathematical reasoning ability.

Natural Language ProcessingTransformersMultiple Languages

The 5-bit quantized version of DeepSeek-R1-0528, suitable for the MLX framework.

Natural Language ProcessingMlx

Fine-tuned based on the Qwen 3 model with 4B parameters to improve inference and problem-solving abilities

Natural Language ProcessingTransformersEnglish

A 6-bit quantized version converted from the DeepSeek-R1-0528-Qwen3-8B model, suitable for text generation tasks in the MLX framework.

Natural Language ProcessingMlx

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

NVIDIA DeepSeek-R1-0528-FP4 is a quantized version of the DeepSeek R1 0528 model. It uses an optimized Transformer architecture, with weights and activation values quantized to the FP4 data type, significantly reducing disk size and GPU memory requirements. It supports the TensorRT-LLM inference engine for efficient inference.

Natural Language ProcessingSafetensors

A quantized version of the DeepSeek R1 0528 model from DeepSeek AI, an autoregressive language model based on an optimized Transformer architecture, which can be used for commercial and non-commercial purposes.

Natural Language ProcessingSafetensors

DeepSeek-R1-0528 is a minor version upgrade model of the DeepSeek R1 series. It significantly improves the inference depth and ability through increased computing resources and algorithm optimization, and performs excellently in multiple benchmark tests such as mathematics and programming.

Natural Language ProcessingTransformers

AWQ-quantized version of DeepSeek R1 0528, supports full-context-length operation on 8x80GB GPUs using vLLM.

Natural Language ProcessingTransformersMultiple Languages

DeepSeek-R1-0528-AWQ is the AWQ quantized version of DeepSeek R1 0528. Through quantization technology, the model's operating efficiency is improved, code issues are fixed, and more stable services are provided.

Natural Language ProcessingTransformersMultiple Languages

The GPTQ quantized version of the DeepSeek-R1-0528 model, using a quantization scheme of Int4 + selective Int8, which reduces the file size while ensuring the generation quality.

Natural Language ProcessingTransformers

The 4-bit AWQ quantized version of the DeepSeek-R1-0528 671B model, suitable for use on high-end GPU nodes

Natural Language ProcessingTransformers

DeepSeek-R1-0528 is a minor version upgrade of the DeepSeek R1 model. It significantly improves the reasoning ability through increased computing resources and algorithm optimization, and performs excellently in multiple benchmark evaluations such as mathematics, programming, and general logic.

Natural Language ProcessingTransformers

The DeepSeek-R1-0528 model after quantization processing significantly reduces the requirements for GPU memory and disk space by quantizing the weights to the INT4 data type.

Natural Language ProcessingSafetensors

The AWQ quantized version of DeepSeek-R1-0528-Qwen3-8B, suitable for efficient inference in specific scenarios.

Natural Language ProcessingTransformers

A quantized version model developed based on DeepSeek-R1-0528-Qwen3-8B, with significant improvements in reasoning ability and reduction of hallucination rate, suitable for various natural language processing tasks.

Natural Language ProcessingTransformers

This is the 4-bit quantized version of the DeepSeek-R1-0528-Qwen3-8B model in MNN format, optimized for efficient inference. Based on the Qwen3-8B architecture, it supports text generation and dialogue functions, suitable for resource-constrained environments.

This is an 8-bit quantized version in MLX format converted from the DeepSeek-R1-0528-Qwen3-8B model, suitable for text generation tasks.

Natural Language ProcessingMlx