dasanindya15/llama2-7b_qlora_Cladder_v1

Loading Model and Tokenizer:

import os
import pandas as pd
import torch
from datasets import load_dataset, Dataset
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
    HfArgumentParser,
)
from peft import LoraConfig, PeftModel

base_model_name = "NousResearch/Llama-2-7b-chat-hf"
finetuned_model = "dasanindya15/llama2-7b_qlora_Cladder_v1"

# Load the entire model on the GPU 0
device_map = {"": 0}

# Reload model in FP16 and merge it with LoRA weights
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_name,
    low_cpu_mem_usage=True,
    return_dict=True,
    torch_dtype=torch.float16,
    device_map=device_map,
)
model = PeftModel.from_pretrained(base_model, finetuned_model)
model = model.merge_and_unload()

# Reload tokenizer to save it
tokenizer = AutoTokenizer.from_pretrained(base_model_name, trust_remote_code=True)
tokenizer.add_special_tokens({'pad_token': '[PAD]'})
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "right"

---

license: mit

datasets: dasanindya15/Cladder_v1

pipeline_tag: text-generation

---