NLPark/Test1_SLIDE

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:Apr 21, 2024License:cc-by-nc-sa-4.0Architecture:Transformer Open Weights Warm

NLPark/Test1_SLIDE is an 8 billion parameter language model developed by NLPark, based on the Meta-Llama-3-8B architecture. This model is an early preview from the "Shi-Ci" series, designed for language identification and decoding, supporting both Chinese and English. It focuses on demonstrating initial capabilities for multilingual processing within the v3 LLM product line.

Loading preview...

NLPark/Test1_SLIDE: Shi-Ci Language Identify & Decode Expositor

NLPark/Test1_SLIDE is an 8 billion parameter language model, serving as an early preview within NLPark's v3 LLM series. This model is built upon the robust Meta-Llama-3-8B architecture, indicating a strong foundation for its capabilities. It is specifically designed for language identification and decoding, with initial support for both Chinese and English languages.

Key Capabilities

  • Multilingual Processing: Focuses on handling and interpreting content in Chinese and English.
  • Language Identification: A core function is to accurately identify the language of input text.
  • Decoding Expositor: Aims to decode and process linguistic information effectively.
  • Early v3 Series Preview: Represents the initial release from NLPark's upcoming v3 LLM product lines, which include "Shi-Ci", "AnFeng", and "Cecilia" series.

Good For

  • Developers exploring early versions of NLPark's v3 multilingual LLMs.
  • Applications requiring basic language identification and decoding in Chinese and English.
  • Testing and evaluating foundational models based on the Llama 3 architecture for specific linguistic tasks.

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