arabellako22/chyon_gemma_4_gguf

Chyon-Gemma-4 GGUF

This is a merged and quantized GGUF version of the LoRA fine-tuned model.

Source

• Base model: unsloth/gemma-4-E2B-it
• LoRA adapter: arabellako22/chyon_lora_model
• Merged full model: arabellako22/chyon_merged_full_gemma_4

Files

• chyon-gemma-4.Q4_K_M.gguf: recommended local version
• chyon-gemma-4.Q5_K_M.gguf: better quality, larger size

Recommended prompt template

Use the same Gemma-style template used during training:

<start_of_turn>user
{{ system_prompt }}

{{ user_prompt }}<end_of_turn>
<start_of_turn>model