refarde/Mistral-7B-Instruct-v0.2-Ko-S-Core

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kPublished:Jan 14, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

refarde/Mistral-7B-Instruct-v0.2-Ko-S-Core is a 7 billion parameter instruction-tuned causal language model based on Mistral-7B-Instruct-v0.2. This model is specifically fine-tuned for Korean language tasks, leveraging the ko-alpaca dataset. It offers a context length of 8192 tokens, making it suitable for applications requiring Korean language understanding and generation.

Loading preview...

Overview

refarde/Mistral-7B-Instruct-v0.2-Ko-S-Core is an instruction-tuned language model built upon the robust Mistral-7B-Instruct-v0.2 architecture. With 7 billion parameters and an 8192-token context window, this model is designed for efficient performance.

Key Capabilities

  • Korean Language Proficiency: Specifically fine-tuned using the royboy0416/ko-alpaca dataset, enhancing its ability to understand and generate text in Korean.
  • Instruction Following: Inherits strong instruction-following capabilities from its base model, making it effective for various prompt-based tasks.

Good For

  • Korean NLP Applications: Ideal for tasks such as text generation, summarization, translation, and question-answering in Korean.
  • Research and Development: Provides a solid foundation for further fine-tuning or experimentation with Korean language models.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p