Analyze this codebase and create a multi-level interactive dependency graph visualization as a single HTML file.
Level 1 - System Overview (40,000ft view):
Level 2 - Module View (10,000ft view):
Paste it to settings.json:
"github.copilot.chat.commitMessageGeneration.instructions": [
{
"text": "Follow the Conventional Commits format strictly for commit messages. Use the structure below:\n\n```\n<type>[optional scope]: <gitmoji> <description>\n\n[optional body]\n```\n\nGuidelines:\n\n1. **Type and Scope**: Choose an appropriate type (e.g., `feat`, `fix`) and optional scope to describe the affected module or feature.\n\n2. **Gitmoji**: Include a relevant `gitmoji` that best represents the nature of the change.\n\n3. **Description**: Write a concise, informative description in the header; use backticks if referencing code or specific terms.\n\n4. **Body**: For additional details, use a well-structured body section:\n - Use bullet points (`*`) for clarity.\n - Clearly describe the motivation, context, or technical details behind the change, if applicable.\n\nCommit messages should be clear, informative, and professional, aiding readability and project tracking."
}
]
| 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 |
| # 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 = """ |
| 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 |
| 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 |
| 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)) |
| # 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) |
| 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() |