CreitinGameplays/tesy-0.2

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Feb 5, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

CreitinGameplays/tesy-0.2 is an 8 billion parameter Llama 3.1 instruction-tuned causal language model developed by CreitinGameplays. This model was finetuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general instruction-following tasks, leveraging the Llama 3.1 architecture for robust performance.

Loading preview...

CreitinGameplays/tesy-0.2: A Finetuned Llama 3.1 Model

CreitinGameplays/tesy-0.2 is an 8 billion parameter instruction-tuned language model, building upon the robust Llama 3.1 architecture. Developed by CreitinGameplays, this model was finetuned with a focus on efficiency, utilizing the Unsloth library in conjunction with Huggingface's TRL. This combination allowed for a reported 2x acceleration in the training process, making it a notable example of optimized finetuning.

Key Capabilities

  • Instruction Following: As an instruction-tuned model, it is designed to understand and execute a wide range of user prompts and commands.
  • Llama 3.1 Foundation: Benefits from the advanced capabilities and general knowledge encoded within the Meta Llama 3.1 base model.
  • Efficient Training: Leverages Unsloth for faster finetuning, which can be advantageous for developers looking to quickly adapt Llama models.

Good For

  • General Purpose AI Applications: Suitable for various tasks requiring a capable instruction-following LLM.
  • Developers Prioritizing Training Speed: Ideal for those who need to quickly iterate on finetuned Llama 3.1 models.
  • Experimentation with Unsloth: Provides a practical example of a model trained using the Unsloth framework for performance optimization.