atasoglu/Turkish-Llama-3-8B-function-calling

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Mar 31, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

The atasoglu/Turkish-Llama-3-8B-function-calling model is an 8 billion parameter Llama-3 based language model developed by atasoglu. It is fine-tuned specifically for Turkish function calling tasks, adapting from ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1. This model leverages Unsloth for faster training and is optimized to generate appropriate JSON function calls based on Turkish user queries.

Loading preview...

Model Overview

The atasoglu/Turkish-Llama-3-8B-function-calling is an 8 billion parameter Llama-3 based language model developed by atasoglu. It has been specifically fine-tuned for Turkish function calling tasks, building upon the ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1 model. The fine-tuning process utilized the atasoglu/turkish-function-calling-20k dataset and was accelerated using Unsloth and Huggingface's TRL library.

Key Capabilities

  • Turkish Function Calling: Designed to understand Turkish natural language queries and translate them into structured JSON function calls.
  • Llama-3 Architecture: Benefits from the robust Llama-3 base model for strong language understanding.
  • Optimized Training: Achieved 2x faster training through the integration of Unsloth.

Good For

  • Developing Turkish-speaking AI assistants: Ideal for applications requiring AI to interact with external tools or APIs based on Turkish user input.
  • Automating tasks in Turkish: Can be used to trigger specific actions or retrieve information by parsing Turkish commands into function calls.
  • Research in multilingual function calling: Provides a specialized model for studying and advancing function calling capabilities in non-English languages, particularly Turkish.

Finetunes
1 models