改善大型语言模型的3种简单方法

from huggingface_hub import notebook_login
notebook_login()

from torch import cuda, bfloat16
import transformers

model_id = 'meta-llama/Llama-2-13b-chat-hf'
pyt
# 4-bit Quanityzation to load Llama 2 with less GPU memory
bnb_config = transformers.BitsAndBytesConfig(
    load_in_4bit=True,  
    bnb_4bit_quant_type='nf4',  
    bnb_4bit_use_double_quant=True,
    bnb_4bit_compute_dtype=bfloat16
)

# Llama 2 Tokenizer
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)

# Llama 2 Model
model = transformers.AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    quantization_config=bnb_config,
    device_map='auto',
)
model.eval()

# Our text generator
generator = transformers.pipeline(
    model=model, tokenizer=tokenizer,
    task='text-generation',
    temperature=0.1,
    max_new_tokens=500,
    repetition_penalty=1.1
)

basic_prompt = """
<s>[INST] <<SYS>>

You are a helpful assistant

<</SYS>>

What is 1 + 1? [/INST]
"""
print(generator(basic_prompt)[0]["generated_text"])

"""
Oh my, that's a simple one! 
The answer to 1 + 1 is... (drumroll please)... 2! 😄
"""

prompt = """
<s>[INST] <<SYS>>

You are a helpful assistant.

<</SYS>>

Classify the text into neutral, negative or positive. 
Text: I think the food was okay. [/INST]
"""
print(generator(prompt)[0]["generated_text"])

"""
Positive. The word "okay" is a mildly positive word, 
indicating that the food was satisfactory or acceptable.
"""

prompt = """
<s>[INST] <<SYS>>

You are a helpful assistant.

<</SYS>>

Classify the text into neutral, negative or positive. 
Text: I think the food was alright.
Sentiment: 
[/INST] 

Neutral</s><s>

[INST]
Classify the text into neutral, negative or positive. 
Text: I think the food was okay.
Sentiment: 
[/INST] 
"""
print(generator(prompt)[0]["generated_text"])

"""
Neutral
"""

prompt = """
<s>[INST] <<SYS>>

You are a helpful assistant.

<</SYS>>

Do the odd numbers in this group add up to an even number? 3, 5, 15, 32.
Solve by breaking the problem into steps. 
Identify the odd numbers, add them, and indicate whether the result is odd or even.[/INST]
"""
print(generator(prompt)[0]["generated_text"])

"""
Hello! I'd be happy to help you with that. Let's break down the problem into steps:

Step 1: Identify the odd numbers in the group.

The odd numbers in the group are:

3, 5, 15

Step 2: Add the odd numbers.

3 + 5 + 15 = 23

Step 3: Is the result odd or even?

23 is an odd number.

Therefore, the sum of the odd numbers in the group is an odd number.
"""

# Our tiny knowledge base
knowledge_base = [
    "On July 18, 2023, in partnership with Microsoft, Meta announced LLaMA-2, the next generation of LLaMA." ,
    "Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ",
    "The fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases.",
    "Meta trained and released LLaMA-2 in three model sizes: 7, 13, and 70 billion parameters.",
    "The model architecture remains largely unchanged from that of LLaMA-1 models, but 40% more data was used to train the foundational models.",
    "The accompanying preprint also mentions a model with 34B parameters that might be released in the future upon satisfying safety targets."
]
with open(r'knowledge_base.txt', 'w') as fp:
    fp.write('\n'.join(knowledge_base))

from langchain.embeddings.huggingface import HuggingFaceEmbeddings

# Embedding Model for converting text to numerical representations
embedding_model = HuggingFaceEmbeddings(
    model_name='sentence-transformers/all-MiniLM-L6-v2'
)

from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.document_loaders import TextLoader

# Load documents and split them
documents = TextLoader("knowledge_base.txt").load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

# Create local vector database
db = FAISS.from_documents(docs, embedding_model)

from langchain.chains import RetrievalQA
from langchain.llms import HuggingFacePipeline

# Load LLM into LangChain
llm = HuggingFacePipeline(pipeline=generator)

# RAG Pipeline
rag = RetrievalQA.from_chain_type(
    llm=llm, chain_type='stuff',
    retriever=db.as_retriever()
)

>>> llm('What is Llama 2?')

"""
Llama 2 is a cryptocurrency that was created as a parody of the popular cryptocurrency Dogecoin. It was designed to be a more serious and less meme-focused alternative to Dogecoin, with a focus on privacy and security.
Llama 2 uses a proof-of-work consensus algorithm and has a block time of 1 minute. It also features a decentralized governance system that allows holders of the llama2 token to vote on proposals for the development and growth of the project.
One of the key features of Llama 2 is its use of "ring signatures" to enhance privacy and security. Ring signatures are a type of digital signature that can be used to hide the identity of the sender in a transaction. This makes it more difficult for hackers or other malicious actors to trace the source of a transaction.
Overall, Llama 2 is a privacy-focused cryptocurrency that is designed to provide users with greater control over their financial data and more secure transactions.
"""

>>> rag('What is Llama 2?')

"""
Llama 2 is a collection of pretrained and fine-tuned large language models 
(LLMs) announced by Meta in partnership with Microsoft on July 18, 2023.
"""

import langchain
langchain.debug = True

import pandas as pd
from datasets import load_dataset

# Load dataset in pandas
dataset = load_dataset("timdettmers/openassistant-guanaco")
df = pd.DataFrame(dataset["train"][:1000]).dropna()
df.to_csv("train.csv")

autotrain llm --train \
--project_name Llama-Chat \
--model abhishek/llama-2-7b-hf-small-shards \
--data_path . \
--use_peft \
--use_int4 \
--learning_rate 2e-4 \
--num_train_epochs 1 \
--trainer sft \
--merge_adapter