Eurdem/Defne-llama3.1-8B

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Jul 29, 2024License:llama3.1Architecture:Transformer0.0K Warm

Eurdem/Defne-llama3.1-8B is an 8 billion parameter instruction-tuned causal language model, fine-tuned from Meta-Llama-3.1-8B-Instruct. It was further merged with VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct and specifically trained on a 4 million token Turkish dataset. This model excels in both English and Turkish language generation, making it suitable for multilingual conversational AI applications requiring a 32768 token context length.

Loading preview...

Overview

Eurdem/Defne-llama3.1-8B is an 8 billion parameter instruction-tuned language model, building upon the Meta-Llama-3.1-8B-Instruct architecture. This model has undergone a specialized fine-tuning process, incorporating a substantial Turkish dataset of approximately 4 million tokens. Following this, it was merged with VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct, enhancing its capabilities.

Key Capabilities

  • Multilingual Generation: Demonstrates proficiency in generating responses in both English and Turkish, as evidenced by provided examples.
  • Instruction Following: Designed to follow instructions effectively, suitable for chatbot applications.
  • Mathematical Reasoning: Capable of performing basic mathematical calculations, such as evaluating functions.
  • Extended Context: Supports a context length of 32768 tokens, allowing for processing longer inputs and generating more coherent, extended outputs.

Good For

  • Turkish Language Applications: Ideal for chatbots, customer service, and content generation tasks requiring strong Turkish language understanding and generation.
  • Multilingual Chatbots: Suitable for developing conversational AI agents that need to operate in both English and Turkish environments.
  • Instruction-Based Tasks: Effective for scenarios where the model needs to adhere to specific user instructions or system prompts.

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