LLM 以称为 token 的块的形式来处理输入和输出,每个模型都有自己的 tokenization 方案。比如下面这句话:
Our destiny is written in the stars.
Llama 2 的 tokenization 为 ["our", "dest", "iny", "is", "writing", "in", "the", "stars"]。考虑 API 定价和内部行为(例如超参数)时,token 显得尤为重要。每个模型都有一个 prompt 不能超过的最大上下文长度,Llama 2 是 4096 个 token,而 Code Llama 是 100K 个 token。
pip install langchain replicate
from typing import Dict, List
from langchain.llms import Replicate
from langchain.memory import ChatMessageHistory
from langchain.schema.messages import get_buffer_string
import os
# Get a free API key from https://replicate.com/account/api-tokens
os.environ ["REPLICATE_API_TOKEN"] = "YOUR_KEY_HERE"
LLAMA2_70B_CHAT = "meta/llama-2-70b-chat:2d19859030ff705a87c746f7e96eea03aefb71f166725aee39692f1476566d48"
LLAMA2_13B_CHAT = "meta/llama-2-13b-chat:f4e2de70d66816a838a89eeeb621910adffb0dd0baba3976c96980970978018d"
# We'll default to the smaller 13B model for speed; change to LLAMA2_70B_CHAT for more advanced (but slower) generations
DEFAULT_MODEL = LLAMA2_13B_CHAT
def completion (
prompt: str,
model: str = DEFAULT_MODEL,
temperature: float = 0.6,
top_p: float = 0.9,
) -> str:
llm = Replicate (
model=model,
model_kwargs={"temperature": temperature,"top_p": top_p, "max_new_tokens": 1000}
)
return llm (prompt)
def chat_completion (
messages: List [Dict],
model = DEFAULT_MODEL,
temperature: float = 0.6,
top_p: float = 0.9,
) -> str:
history = ChatMessageHistory ()
for message in messages:
if message ["role"] == "user":
history.add_user_message (message ["content"])
elif message ["role"] == "assistant":
history.add_ai_message (message ["content"])
else:
raise Exception ("Unknown role")
return completion (
get_buffer_string (
history.messages,
human_prefix="USER",
ai_prefix="ASSISTANT",
),
model,
temperature,
top_p,
)
def assistant (content: str):
return { "role": "assistant", "content": content }
def user (content: str):
return { "role": "user", "content": content }
def complete_and_print (prompt: str, model: str = DEFAULT_MODEL):
print (f'==============\n {prompt}\n==============')
response = completion (prompt, model)
print (response, end='\n\n')
complete_and_print ("The typical color of the sky is:")
complete_and_print ("which model version are you?")
response = chat_completion (messages=[
user ("My favorite color is blue."),
assistant ("That's great to hear!"),
user ("What is my favorite color?"),
])
print (response)
# "Sure, I can help you with that! Your favorite color is blue."
def print_tuned_completion (temperature: float, top_p: float):
response = completion ("Write a haiku about llamas", temperature=temperature, top_p=top_p)
print (f'[temperature: {temperature} | top_p: {top_p}]\n {response.strip ()}\n')
print_tuned_completion (0.01, 0.01)
print_tuned_completion (0.01, 0.01)
# These two generations are highly likely to be the same
print_tuned_completion (1.0, 1.0)
print_tuned_completion (1.0, 1.0)
# These two generations are highly likely to be different
complete_and_print (prompt="Describe quantum physics in one short sentence of no more than 12 words")
# Returns a succinct explanation of quantum physics that mentions particles and states existing simultaneously.
风格化,例如: 向我解释一下这一点,就像儿童教育网络节目中教授小学生一样; 我是一名软件工程师,使用大型语言模型进行摘要。用 250 字概括以下文字; 像私家侦探一样一步步追查案件,给出你的答案。
格式化 使用要点; 以 JSON 对象形式返回; 使用较少的技术术语并用于工作交流中。
限制 仅使用学术论文; 切勿提供 2020 年之前的来源; 如果你不知道答案,就说你不知道。
complete_and_print ("Explain the latest advances in large language models to me.")
# More likely to cite sources from 2017
complete_and_print ("Explain the latest advances in large language models to me. Always cite your sources. Never cite sources older than 2020.")
# Gives more specific advances and only cites sources from 2020
complete_and_print ("Text: This was the best movie I've ever seen! \n The sentiment of the text is:")
# Returns positive sentiment
complete_and_print ("Text: The director was trying too hard. \n The sentiment of the text is:")
# Returns negative sentiment
def sentiment (text):
response = chat_completion (messages=[
user ("You are a sentiment classifier. For each message, give the percentage of positive/netural/negative."),
user ("I liked it"),
assistant ("70% positive 30% neutral 0% negative"),
user ("It could be better"),
assistant ("0% positive 50% neutral 50% negative"),
user ("It's fine"),
assistant ("25% positive 50% neutral 25% negative"),
user (text),
])
return response
def print_sentiment (text):
print (f'INPUT: {text}')
print (sentiment (text))
print_sentiment ("I thought it was okay")
# More likely to return a balanced mix of positive, neutral, and negative
print_sentiment ("I loved it!")
# More likely to return 100% positive
print_sentiment ("Terrible service 0/10")
# More likely to return 100% negative
complete_and_print ("Explain the pros and cons of using PyTorch.")
# More likely to explain the pros and cons of PyTorch covers general areas like documentation, the PyTorch community, and mentions a steep learning curve
complete_and_print ("Your role is a machine learning expert who gives highly technical advice to senior engineers who work with complicated datasets. Explain the pros and cons of using PyTorch.")
# Often results in more technical benefits and drawbacks that provide more technical details on how model layers
complete_and_print ("Who lived longer Elvis Presley or Mozart?")
# Often gives incorrect answer of "Mozart"
complete_and_print ("Who lived longer Elvis Presley or Mozart? Let's think through this carefully, step by step.")
# Gives the correct answer "Elvis"
import re
from statistics import mode
def gen_answer ():
response = completion (
"John found that the average of 15 numbers is 40."
"If 10 is added to each number then the mean of the numbers is?"
"Report the answer surrounded by three backticks, for example:```123```",
model = LLAMA2_70B_CHAT
)
match = re.search (r'```(\d+)```', response)
if match is None:
return None
return match.group (1)
answers = [gen_answer () for i in range (5)]
print (
f"Answers: {answers}\n",
f"Final answer: {mode (answers)}",
)
# Sample runs of Llama-2-70B (all correct):
# [50, 50, 750, 50, 50] -> 50
# [130, 10, 750, 50, 50] -> 50
# [50, None, 10, 50, 50] -> 50
complete_and_print ("What is the capital of the California?", model = LLAMA2_70B_CHAT)
# Gives the correct answer "Sacramento"
complete_and_print ("What was the temperature in Menlo Park on December 12th, 2023?")
# "I'm just an AI, I don't have access to real-time weather data or historical weather records."
complete_and_print ("What time is my dinner reservation on Saturday and what should I wear?")
# "I'm not able to access your personal information [..] I can provide some general guidance"
MENLO_PARK_TEMPS = {
"2023-12-11": "52 degrees Fahrenheit",
"2023-12-12": "51 degrees Fahrenheit",
"2023-12-13": "51 degrees Fahrenheit",
}
def prompt_with_rag (retrived_info, question):
complete_and_print (
f"Given the following information: '{retrived_info}', respond to: '{question}'"
)
def ask_for_temperature (day):
temp_on_day = MENLO_PARK_TEMPS.get (day) or "unknown temperature"
prompt_with_rag (
f"The temperature in Menlo Park was {temp_on_day} on {day}'", # Retrieved fact
f
"What is the temperature in Menlo Park on {day}?", # User question
)
ask_for_temperature ("2023-12-12")
# "Sure! The temperature in Menlo Park on 2023-12-12 was 51 degrees Fahrenheit."
ask_for_temperature ("2023-07-18")
# "I'm not able to provide the temperature in Menlo Park on 2023-07-18 as the information provided states that the temperature was unknown."
complete_and_print ("""
Calculate the answer to the following math problem:
((-5 + 93 * 4 - 0) * (4^4 + -7 + 0 * 5))
""")
# Gives incorrect answers like 92448, 92648, 95463
complete_and_print (
"""
# Python code to calculate: ((-5 + 93 * 4 - 0) * (4^4 + -7 + 0 * 5))
""",
model="meta/codellama-34b:67942fd0f55b66da802218a19a8f0e1d73095473674061a6ea19f2dc8c053152"
)
# The following code was generated by Code Llama 34B:
num1 = (-5 + 93 * 4 - 0)
num2 = (4**4 + -7 + 0 * 5)
answer = num1 * num2
print (answer)