Low Rank Adapter for Bloom decoder for question answering
Example usage:
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
from IPython.display import display, Markdown
peft_model_id = "Jayveersinh-Raj/bloom-que-ans"
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=False, device_map='auto')
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
# Load the Lora model
qa_model = PeftModel.from_pretrained(model, peft_model_id)
def make_inference(context, question):
batch = tokenizer(f"### CONTEXT\n{context}\n\n### QUESTION\n{question}\n\n### ANSWER\n", return_tensors='pt').to("cuda")
with torch.cuda.amp.autocast():
output_tokens = qa_model.generate(**batch, max_new_tokens=200)
display(Markdown((tokenizer.decode(output_tokens[0], skip_special_tokens=True))))
context = ""
question = "What is the best food?"
make_inference(context, question)
- Downloads last month
- 2
Model tree for Jayveersinh-Raj/bloom-que-ans
Base model
bigscience/bloom-3b
Adapter
this model