suarkadipa/gpt-neox-20b-Medical-reports-Splits

How to run in Google Colab

Note: must be run in GPU

!pip install -q -U bitsandbytes
!pip install -q -U git+https://github.com/huggingface/transformers.git 
!pip install -q -U git+https://github.com/huggingface/peft.git

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

model_id = "EleutherAI/gpt-neox-20b"
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0})

from peft import LoraConfig, get_peft_model

lora_config = LoraConfig.from_pretrained('suarkadipa/gpt-neox-20b-Medical-reports-Splits')
model = get_peft_model(model, lora_config)

text = "The lungs "
device = "cuda:0"

inputs = tokenizer(text, return_tensors="pt").to(device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

#output example: The lungs are the organs that are most affected by the disease. The disease can cause the lungs to become inflamed, which can lead to pneumonia.