malhajar/Mistral-7B-Instruct-v0.2-turkish

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

malhajar/Mistral-7B-Instruct-v0.2-turkish is a 7 billion parameter instruction-tuned causal language model developed by Mohamad Alhajar. It is a finetuned version of Mistral-7B-Instruct-v0.2, specifically optimized for generating responses in Turkish. This model excels at answering instructions and information requests in a chat format, leveraging its training on the alpaca-gpt4-tr dataset.

Loading preview...

Model Overview

malhajar/Mistral-7B-Instruct-v0.2-turkish is a 7 billion parameter instruction-tuned language model developed by Mohamad Alhajar. It is a specialized adaptation of the Mistral-7B-Instruct-v0.2 base model, finetuned using SFT Training and the Freeze method.

Key Capabilities

  • Turkish Language Proficiency: Specifically optimized for understanding and generating responses in Turkish.
  • Instruction Following: Designed to accurately follow and respond to instructions in a chat-based format.
  • Chatbot Applications: Well-suited for conversational AI tasks where Turkish language interaction is required.

Training Details

The model was finetuned on the alpaca-gpt4-tr dataset, which focuses on Turkish instructions. This targeted training enhances its performance for Turkish-specific use cases, differentiating it from its base model.

Prompt Format

Users should structure prompts using the following template for optimal performance:

### Instruction:
<prompt>
### Response:

This model is ideal for developers looking to integrate a capable, Turkish-centric instruction-following LLM into their applications.