from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM

# Load base model in 4 bit
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf", load_in_4bit=True)

# Wrap model with pretrained model weights
config = PeftConfig.from_pretrained("MaziyarPanahi/Llama-2-7b-hf-codealpaca-4bit")
model = PeftModel.from_pretrained(model, "MaziyarPanahi/Llama-2-7b-hf-codealpaca-4bit", config=config)

Prompt Template:

Below is an instruction that describes a task, paired with an input
that provides further context. Write a response that appropriately
completes the request.
### Instruction: {instruction}
### Input: {input}
### Response:

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: float16

Framework versions

PEFT 0.7.1