occiglot/occiglot-7b-fr-en-instruct

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Mar 5, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Occiglot-7B-FR-EN-Instruct is a 7 billion parameter instruction-tuned causal decoder-only transformer language model developed by the Occiglot Research Collective. It supports English, Spanish, and code, and was fine-tuned on 160M additional multilingual and code instructions. This model is designed for generative tasks in these languages, offering a specialized solution for applications requiring instruction-following capabilities in a multilingual context.

Loading preview...

Occiglot-7B-FR-EN-Instruct Overview

Occiglot-7B-FR-EN-Instruct is a 7 billion parameter instruction-tuned language model from the Occiglot Research Collective. It is built upon the occiglot-7b-fr-en base model and has been further trained on 160 million tokens of additional multilingual and code instructions. This model is specifically designed to support English, Spanish, and code-related tasks.

Key Capabilities

  • Multilingual Instruction Following: Excels at understanding and executing instructions in both English and Spanish.
  • Code Generation: Capable of handling code-related prompts and generating code outputs.
  • Causal Language Modeling: Functions as a causal decoder-only transformer, suitable for generative tasks.

Good For

  • Applications requiring instruction-tuned responses in English and Spanish.
  • Developing multilingual chatbots or assistants.
  • Code generation and understanding tasks within its supported languages.
  • Research into multilingual LLMs, particularly for Western languages.

Note: This model was not safety aligned and may produce problematic outputs. It represents the first release of an ongoing open research project.