Supergene/DeepSeek-R1-Distill-Qwen-32B-Japanese

TEXT GENERATIONPricing:Input $2.72 / Output $4.8Concurrent Unit Cost:2Model Size:32.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 23, 2025License:mitArchitecture:Transformer Open Weights Featherless Exclusive Cold

Supergene/DeepSeek-R1-Distill-Qwen-32B-Japanese is a 32.8 billion parameter Japanese-finetuned causal language model based on DeepSeek-R1-Distill-Qwen-32B. Developed by Ryosuke Ishigami, this model specializes in Japanese language understanding and generation. It leverages the DeepSeek-R1 architecture, which is designed to enhance reasoning capabilities in large language models. This model is primarily intended for applications requiring high-quality Japanese text processing.

Loading preview...

DeepSeek-R1-Distill-Qwen-32B-Japanese Overview

This model is a 32.8 billion parameter large language model specifically finetuned for the Japanese language. It is built upon the deepseek-ai/DeepSeek-R1-Distill-Qwen-32B architecture, which is known for its focus on improving reasoning capabilities in LLMs. The model was developed by Ryosuke Ishigami.

Key Capabilities

  • Japanese Language Proficiency: Optimized for understanding and generating high-quality Japanese text.
  • Causal Language Modeling: Capable of generating coherent and contextually relevant text based on given prompts.
  • DeepSeek-R1 Foundation: Benefits from the underlying DeepSeek-R1 architecture, which aims to enhance reasoning skills.

Good For

  • Japanese NLP Applications: Ideal for tasks such as text generation, summarization, translation, and conversational AI in Japanese.
  • Research and Development: Suitable for researchers exploring large language models with a strong Japanese language focus.
  • Content Creation: Can be used to generate various forms of Japanese content, from creative writing to informational texts.

Finetunes
1 models