NickyNicky/gemma-2b-it_oasst2_chatML_Cluster2_aya_multilingual
Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2.5BQuant:BF16Ctx Length:8kPublished:Mar 1, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

NickyNicky/gemma-2b-it_oasst2_chatML_Cluster2_aya_multilingual is a 2.5 billion parameter instruction-tuned causal language model developed by NickyNicky, based on Google's Gemma-2b-it. This model is fine-tuned on a combination of Oasst2 and Aya multilingual datasets, specifically optimized for multilingual chat interactions across 20+ languages including Spanish, English, French, and German. It features an 8192-token context length and is designed to improve control over responses in various languages, making it suitable for diverse international applications.

Loading preview...

Overview

NickyNicky/gemma-2b-it_oasst2_chatML_Cluster2_aya_multilingual is a 2.5 billion parameter instruction-tuned language model built upon Google's Gemma-2b-it architecture. This model has been specifically fine-tuned using a combination of the NickyNicky/aya_dataset_multilingual_chatml_gemma and CohereForAI/aya_dataset datasets, with a focus on enhancing multilingual chat capabilities. It supports over 20 languages, including Bulgarian, Catalan, Czech, Danish, German, English, Spanish, French, Croatian, Hungarian, Italian, Dutch, Polish, Portuguese, Romanian, Russian, Slovenian, Serbian, Swedish, and Ukrainian.

Key Capabilities

  • Multilingual Chat: Optimized for generating controlled and coherent responses across a wide array of languages.
  • Instruction Following: Fine-tuned to accurately follow instructions in a chat-ML format.
  • Context Handling: Features an 8192-token context length, allowing for more extensive conversations.
  • Flash Attention 2: Utilizes flash_attention_2 for potentially faster inference.

Good for

  • International Chatbots: Ideal for developing AI assistants that need to interact effectively in multiple languages.
  • Multilingual Content Generation: Suitable for generating text, stories, or responses in various linguistic contexts.
  • Language Translation Assistance: Can be used as a component in systems requiring nuanced language understanding and generation across different languages.
  • Research and Development: Provides a strong base for further experimentation and fine-tuning on specific multilingual tasks.
Finetunes
3 models