metadata
library_name: transformers
language:
- ko
base_model:
- nlpai-lab/KULLM3
Model Details
KULLM3_dialogue_summarization_bnb_4bit
KULLM3_dialogue_summarization_bnb_4bit is continued pretrained(4bit quantization fine-tuned) language model based on KULLM3.
This model is trained fully with publicily available resource at HuggingFace dataset hub, preprocessed Korean texts.
The train was done on RTX 3090 24GB * 1.
Model developers Dongwook Min (mindw96)
Variations KULLM3_dialogue_summarization_bnb_4bit comes in one size — 10.7B.
Input Models input text only.
Output Models generate text only.
Model Architecture KULLM3 is an auto-regressive language model that uses an optimized transformer architecture.
Model Release Date 14.06.2024.
Capabilities
- Summarization