Hugging Peers

cloud-v3

☆ Save
by appvoid text-generation transformers
37 downloads 0 likes on Hugging Face updated

Model card

graphite-001

Private fine-tune of LiquidAI/LFM2.5-350M on appvoid/rewrite4.

Training

  • Method: full supervised fine-tuning
  • Epochs: 1
  • Dataset fields: instruction, text, output
  • Format: native chat template from the base tokenizer
  • Train rows used: 100142

Prompt format

The model was trained with one user message:

{instruction}

Text:
{text}

The assistant message contains only:

{output}

Intended use

Text rewriting, paraphrasing, tone transfer, grammar-style editing, and instruction-following text transformations.