abodacs

You are Manus, an AI agent created by the Manus team.

You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet

abodacs

abodacs

# train_grpo.py
import re
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer

# Load and prep dataset

SYSTEM_PROMPT = """

abodacs

Classify user search queries as either "Good Google Search Query" or "Bad Google Search Query" based on their likelihood of yielding relevant and helpful results from Google Search.

Input: User search query (text string).

Output: Classification label:
    * Good Google Search Query: The query is likely to be effectively answered by Google Search.
    * Bad Google Search Query: The query is unlikely to be effectively answered by Google Search.  Further categorize "Bad" queries into subtypes for better understanding and classifier training (optional but highly recommended):
        * Chit-Chat/Conversational/Social
        * Personal/Subjective/Opinion-Based (Un-searchable)
        * Vague/Ambiguous/Lacking Specificity

abodacs

You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

## Core Principles

1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference

abodacs

import multiprocessing

manager = multiprocessing.Manager()
all_hashes_set = manager.dict()
def deduplicate(examples, all_hashes_set):
    print(len(all_hashes_set))
    input_ids = examples['input_ids']
    hashes = [
        hash(tuple(input_ids[i]))
        for i in range(len(input_ids))

abodacs

# Train GPT-2 in five minutes -- for free
#
# ```bash
# pip install modal
# modal setup
# modal run wrapper.py
# ```
#
# Note that the end-to-end latency the first time is more like 25 minutes:
# - five minutes to install Torch (rip)

abodacs

import torch
from diffusers import FluxPipeline
from torch import nn


class ModelOffloaderV2:
    def __init__(self, model: nn.Module, record_stream: bool = False):
        # move model to pinned memory. keep a model copy in CPU pinned memory.
        for p in model.parameters():
            p.data = p.data.cpu().pin_memory()

abodacs

require("dotenv").config();
const H = require("highland");
const axios = require("axios");
const fs = require("fs").promises;

const exportDirectory = "./export";
const apiUrl = "https://api.intercom.io";

// config axios for the authorized API request
const apiClient = axios.create({

abodacs

var $debugHelper = $debugHelper || {};
$debugHelper = function () {
    var href = "lib/debugger.css";
    var addCss = function () {
        if (styleStyleIsLoaded(href) === true) {
            return;
        }
        const head = document.head;
        const link = document.createElement("link");
        link.type = "text/css";