ArtificialGuyBR

Home / Projects / Gemma 2 2B OpenHermes2.5

LLM · Text Generation

Gemma 2 2B OpenHermes2.5

Gemma 2 2B fine-tuned on OpenHermes-2.5 for instruction following and chat in ChatML format.

About this model

Gemma 2 2B OpenHermes2.5 is a causal language model built by ArtificialGuyBR as a fine-tune of Google's gemma-2-2b base model on the teknium/OpenHermes-2.5 dataset. It is packaged for the transformers text-generation pipeline with safetensors weights, and is optimized for instruction following and general language tasks such as question answering and chat. The OpenHermes-2.5 dataset is primarily GPT-4 synthetic data in ChatML format, so the model inherits that conversational structure: prompts should be wrapped in ChatML system/user/assistant turns rather than plain text.

Learn more

Read the in-depth guide about Gemma 2 2B OpenHermes2.5

Project signals

  • 16 Hugging Face downloads
  • 7 Hugging Face likes

Topics

transformers · safetensors · gemma2 · text-generation · gemma · instruct · finetune · chatml · gpt4 · synthetic data

Explore the source