| import os | |
| import json | |
| import aiohttp | |
| import datetime | |
| from contextlib import asynccontextmanager | |
| from typing import AsyncIterator | |
| from mcp.server.fastmcp import FastMCP, Context | |
| from mcp.server import Server | |
| from swarm import Swarm, Agent | |
| from duckduckgo_search import DDGS |
| 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 | |
| # | |
| # See https://github.com/willccbb/verifiers for ongoing developments | |
| # | |
| """ | |
| citation: | |
| @misc{brown2025grpodemo, | |
| title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models}, | |
| author={Brown, William}, |
| from diffusers import FluxPipeline, AutoencoderKL | |
| from diffusers.image_processor import VaeImageProcessor | |
| from transformers import T5EncoderModel, T5TokenizerFast, CLIPTokenizer, CLIPTextModel | |
| import torch | |
| import gc | |
| def flush(): | |
| gc.collect() | |
| torch.cuda.empty_cache() |
Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggml-org/llama.cpp#5962
In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.
See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix
| from collections import defaultdict | |
| import random | |
| from huggingface_hub import hf_hub_download | |
| from datasets import Dataset | |
| import numpy as np | |
| import pandas as pd | |
| from transformers import AutoTokenizer | |
| from rich.console import Console | |
| from rich.table import Table | |
| from trl import DPOTrainer |
| from transformers import AutoModelForCausalLM, AutoTokenizer, StaticCache | |
| import torch | |
| from typing import Optional | |
| device = "cuda" | |
| # Copied from the gpt-fast repo | |
| def multinomial_sample_one_no_sync(probs_sort): # Does multinomial sampling without a cuda synchronization | |
| q = torch.empty_like(probs_sort).exponential_(1) | |
| return torch.argmax(probs_sort / q, dim=-1, keepdim=True).to(dtype=torch.int) |
| #!/bin/bash | |
| ### steps #### | |
| # verify the system has a cuda-capable gpu | |
| # download and install the nvidia cuda toolkit and cudnn | |
| # setup environmental variables | |
| # verify the installation | |
| ### | |
| ### to verify your gpu is cuda enable check |
