Saxo/Linkbricks-Horizon-AI-Llama-3.3-Japanese-70B-sft-dpo-base

TEXT GENERATIONPricing:Input $2.6 / Cached $0.52 / Output $3Concurrent Unit Cost:4Model Size:70BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Dec 11, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Saxo/Linkbricks-Horizon-AI-Llama-3.3-Japanese-70B-sft-dpo-base is a 70 billion parameter language model developed by Yunsung Ji (Saxo) at Linkbricks, fine-tuned from meta-llama/Llama-3.3-70B-Instruct. It is specifically enhanced for Japanese, Korean, Chinese, and English cross-language tasks, incorporating 20 million Japanese news and Wiki corpus data. The model excels in high-dimensional analysis of customer reviews, social posts, coding, writing, mathematics, and complex logical reasoning, featuring a 128k context window and Function Calling capabilities.

Loading preview...

Saxo/Linkbricks-Horizon-AI-Llama-3.3-Japanese-70B-sft-dpo-base Overview

This model is a 70 billion parameter language model developed by Yunsung Ji (Saxo), a data scientist at Linkbricks, an AI and big data analytics company. It is built upon the meta-llama/Llama-3.3-70B-Instruct base model and has undergone Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) specifically for Japanese language enhancement, utilizing 8 H100-80G GPUs.

Key Capabilities

  • Multilingual Proficiency: Trained on 20 million Japanese news and Wiki corpus data, alongside diverse task-specific cross-learning data for Japanese, Korean, Chinese, and English. This enables robust performance across these languages.
  • Enhanced Reasoning: Specifically trained with mathematics and logical judgment data to handle complex logical problems effectively.
  • Advanced Text Analysis: Excels in high-dimensional analysis of customer reviews and social media posts.
  • Coding and Writing: Strengthened capabilities in code generation and various writing tasks.
  • Extended Context Window: Features a 128k context window, allowing for processing and understanding longer inputs.
  • Function Calling: Supports Function Calling and Tool Calling, enabling integration with external tools and APIs.

Good For

  • Applications requiring strong multilingual understanding and generation, particularly in Japanese, Korean, Chinese, and English.
  • Tasks involving complex logical reasoning and mathematical problem-solving.
  • Analyzing large volumes of customer feedback, social media data, and other high-dimensional text.
  • Developing applications that require code generation or advanced writing assistance.
  • Use cases benefiting from a large context window for processing extensive documents or conversations.
  • Integrating with external systems via Function Calling for enhanced automation and capabilities.

Finetunes
1 models