shleeeee/mistral-7b-wiki

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kArchitecture:Transformer0.0K Cold

The shleeeee/mistral-7b-wiki model is a 7 billion parameter language model developed by shleeeee (Seunghyeon Lee) and oopsung (Sungwoo Park). It is a fine-tuned version of the Mistral-7B-v0.1 architecture, specifically optimized for Korean language tasks. This model leverages a custom Korean dataset for its fine-tuning, making it particularly suitable for applications requiring Korean language generation and understanding.

Loading preview...

Overview

The shleeeee/mistral-7b-wiki is a 7 billion parameter language model developed by Seunghyeon Lee and Sungwoo Park. It is a fine-tuned variant of the Mistral-7B-v0.1 architecture, specifically adapted for Korean language processing. The model underwent fine-tuning using a custom Korean dataset, focusing on enhancing its performance and understanding within the Korean linguistic context.

Key Capabilities

  • Korean Language Optimization: Fine-tuned on a custom Korean dataset to improve performance in Korean-specific tasks.
  • Mistral-7B-v0.1 Base: Built upon the robust Mistral-7B-v0.1 architecture, inheriting its foundational capabilities.
  • LoRA Fine-tuning: Utilizes LoRA (Low-Rank Adaptation) targeting q_proj, k_proj, v_proj, o_proj, and gate_proj modules for efficient adaptation.

Good For

  • Korean Text Generation: Ideal for generating coherent and contextually relevant text in Korean.
  • Korean NLP Applications: Suitable for various natural language processing tasks where Korean language proficiency is crucial.
  • Research and Development: Provides a specialized base for further research and development in Korean LLMs.

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