This model is an instruction-tuned model of Llama2-70B with our own medical Q&A dataset.

Method

QLoRA

Parameters

• batch_size = 512
• max_steps = 30000
• source_max_len = 512
• target_max_len = 512

Training time

1617017 seconds on NVIDIA A100 x 4 (not fully used)

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 0.4.0