librarian-bot's picture
Librarian Bot: Add base_model information to model
6161112
|
raw
history blame
707 Bytes
metadata
language:
  - pt
library_name: peft
base_model: NousResearch/Nous-Hermes-Llama2-13b

This model was trained with 20k data in Portuguese in a prompt format. It was trained to receive an input dictionary containing: the phrase to be sorted and the class options (including the 'none' class)

Training procedure

The following bitsandbytes quantization config was used during training:

  • load_in_8bit: False
  • load_in_4bit: True
  • llm_int8_threshold: 6.0
  • llm_int8_skip_modules: None
  • llm_int8_enable_fp32_cpu_offload: False
  • llm_int8_has_fp16_weight: False
  • bnb_4bit_quant_type: nf4
  • bnb_4bit_use_double_quant: True
  • bnb_4bit_compute_dtype: bfloat16

Framework versions

  • PEFT 0.4.0