--- license: apache-2.0 language: - en library_name: transformers tags: - 'quantization ' - LLM - Dolly --- Requirements:
!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 !pip install -q -U git+https://github.com/huggingface/accelerate.gitImport this model using:
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
peft_model_id = ""AhmedBou/databricks-dolly-v2-3b_on_NCSS"
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='auto')
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
# Load the Lora model
model = PeftModel.from_pretrained(model, peft_model_id)
Inference using:
batch = tokenizer("“Multiple Regression for Appraisal” -->: ", return_tensors='pt') with torch.cuda.amp.autocast(): output_tokens = model.generate(**batch, max_new_tokens=50) print('\n\n', tokenizer.decode(output_tokens[0], skip_special_tokens=True))Output:
“Multiple Regression for Appraisal” -->: Multiple Regression for Appraisal (MRA) -->: Multiple Regression for Appraisal (MRA) (with Covariates) -->: Multiple Regression for Appraisal (MRA) (with Covariates