llama2-7b-QLoRA-dolly

模型介绍

• 使用模型：LLaMA2-7B
• 微调方法：QLoRA
• 数据集：databricks/databricks-dolly-15k
• 显卡：一张RTX4090
• 目标：对模型进行指令微调

使用方法

• 加载数据

from datasets import load_dataset 
from random import randrange
 
 
# 从hub加载数据集并得到一个样本
dataset = load_dataset("databricks/databricks-dolly-15k", split="train")
sample = dataset[randrange(len(dataset))]

• 模型使用

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name_or_path = "snowfly/llama2-7b-QLoRA-dolly"
tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=model_name_or_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(pretrained_model_name_or_path=model_name_or_path, 
                                  trust_remote_code=True,
                                  low_cpu_mem_usage=True,
                                  torch_dtype=torch.float16,
                                  load_in_4bit=True)
model = model.eval()


prompt = f"""### Instruction:
Use the Input below to create an instruction, which could have been used to generate the input using an LLM. 
 
### Input:
{sample['response']}
 
### Response:
"""
 
input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cuda()

outputs = model.generate(input_ids=input_ids, max_new_tokens=100, do_sample=True, top_p=0.9,temperature=0.9)

print(f"Prompt:\n{sample['response']}\n")
print(f"Generated instruction:\n{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):]}")
print(f"Ground truth:\n{sample['instruction']}")