Phi 1.5 Playtpus

QLoRA trained for 2 epochs.

Built with Axolotl

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • 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 0.6.0.dev0
Downloads last month
4
Safetensors
Model size
1.41B params
Tensor type
FP16
·
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Dataset used to train openaccess-ai-collective/phi-platypus-qlora