harrywang

{"text":"[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<<\/SYS>>\n\nInput:\nAmanda: I baked  cookies. Do you want some?\r\nJerry: Sure!\r\nAmanda: I'll bring you tomorrow :-) [\/INST]\n\nSummary: Amanda baked cookies and will bring Jerry some tomorrow."}
{"text":"[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<<\/SYS>>\n\nInput:\nOlivia: Who are you voting for in this election? \r\nOliver: Liberals as always.\r\nOlivia: Me too!!\r\nOliver: Great [\/INST]\n\nSummary: Olivia and Olivier are voting for liberals in this election. "}
{"text":"[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<<\/SYS>>\n\nInput:\nTim: Hi, what's up?\r\nKim: Bad mood tbh, I was going to do lots of stuff but ended up procrastinating\r\nTim: What did you plan on doing?\r\nKim: Oh you know, uni stuff and unfucking my room\r\nKim: Maybe tomorrow I'll move my ass and do everything\r\nKim: We were going to defrost a fridge so instead of shopping I'll eat some defrosted 

harrywang

make a comparison table to compare the api pricing between claude, mistral, openai, and gemini based on the following data:

Claude 3

MTok = million tokens. All Claude 3 models support vision and 200,000 token context windows.
Light & fast
Haiku
Input: $0.25 / MTok
Output: $1.25 / MTok
Hard-working

harrywang

import torch
import pandas as pd
import logging
import os

from dotenv import load_dotenv
from sendgrid import SendGridAPIClient
from sendgrid.helpers.mail import Mail
from datetime import datetime

harrywang

def consult_oracle():
    import random
    hex = ''

    for i in range(6):  # toss 6 times to get the hex  
        
        toss = 0
        line = 0

        for i in range(3):  # each toss with three coins to generate one line

harrywang

# partial code snippets shown as hints

# voting regressor 
from sklearn.ensemble import VotingRegressor

voting_reg = VotingRegressor(
    estimators = [
        ('lin', lin_reg_pipeline),
        ('svm', svm_reg_pipeline),
        ('sgd', sgd_reg_pipeline),

harrywang

# sgd regression pipeline with grid search
from sklearn.linear_model import SGDRegressor
from sklearn.model_selection import GridSearchCV

param_grid = [
    {
        'sgd_reg__max_iter':[100000, 1000000], # if number is too small, you will get a warning
        'sgd_reg__tol':[1e-10, 1e-3],
        'sgd_reg__eta0':[0.001, 0.01]
    }

harrywang

# example to show how to select features based on type: numerical vs. categorical
import pandas as pd
# load the data
df = pd.read_csv("housing.csv")

# find numerical features and categorical features based on the type of feature
df_num = df.select_dtypes(exclude ='object')
df_cat = df.select_dtypes(include ='object')

# select numerical features and categorical features

harrywang

Setup

Use V3 from Tai:

python -m venv venv
source venv/bin/activate
pip install tensorflow -i https://pypi.tuna.tsinghua.edu.cn/simple/

harrywang

### code snippet ####
from sklearn.linear_model import LinearRegression

lin_reg_full_pipeline = Pipeline(
    steps=[
        ('preprocessor', preprocessor),
        ('lin_reg', LinearRegression()),
    ]
)

harrywang

{
  "responses": [
    {
      "localizedObjectAnnotations": [
        {
          "mid": "/j/5qg9b8",
          "name": "Packaged goods",
          "score": 0.8396697,
          "boundingPoly": {
            "normalizedVertices": [