pacman100

from accelerate import Accelerator
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from torch.distributed.fsdp.fully_sharded_data_parallel import FullyShardedDataParallel as FSDP
import contextlib

MODEL_NAME = "meta-llama/Llama-2-70b-chat-hf"  #"HuggingFaceH4/zephyr-7b-beta"


def main():

pacman100

#!/usr/bin/env python
# coding=utf-8
# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#

pacman100

/*
 * Starter Project for WhatsApp Echo Bot Tutorial
 *
 * Remix this as the starting point for following the WhatsApp Echo Bot tutorial
 *
 */

"use strict";

// Access token for your app

pacman100

accelerator.process_index=0 GPU Memory before entering the loading : 0
accelerator.process_index=0 GPU Memory consumed at the end of the loading (end-begin): 0
accelerator.process_index=0 GPU Peak Memory consumed during the loading (max-begin): 0
accelerator.process_index=0 GPU Total Peak Memory consumed during the loading (max): 0
accelerator.process_index=0 CPU Memory before entering the loading : 926
accelerator.process_index=0 CPU Memory consumed at the end of the loading (end-begin): 26415
accelerator.process_index=0 CPU Peak Memory consumed during the loading (max-begin): 31818
accelerator.process_index=0 CPU Total Peak Memory consumed during the loading (max): 32744
accelerator.process_index=0 model.lm_head.weight=Parameter containing:
tensor([[-0.0179,  0.0201, -0.0273,  ..., -0.0275, -0.0396, -0.0131],

pacman100

# coding=utf-8
# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software

pacman100

import os
import sys
from typing import List

import fire
import torch
import transformers
from datasets import load_dataset, DatasetDict
from transformers import Seq2SeqTrainer, TrainerCallback, TrainingArguments, TrainerState, TrainerControl
from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR

pacman100

import os
import sys
from typing import List

import fire
import torch
import transformers
from datasets import load_dataset, DatasetDict
from transformers import Seq2SeqTrainer, TrainerCallback, TrainingArguments, TrainerState, TrainerControl
from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR

pacman100

─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /tmp/ipykernel_2299032/1843815119.py:2 in <module>                                               │
│                                                                                                  │
│ [Errno 2] No such file or directory: '/tmp/ipykernel_2299032/1843815119.py'                      │
│                                                                                                  │
│ /home/sourab/miniconda3/envs/ml/lib/python3.10/site-packages/optimum/onnxruntime/modeling_ort.py │
│ :581 in from_pretrained                                                                          │
│                                                                                                  │
│    578 │   │   Returns:                                                                          │
│    579 │   │   │   `ORTModel`: The loaded ORTModel model.                                        │

pacman100

import gc
import os
import sys
import psutil
import threading
import argparse
import transformers
import datasets
import numpy as np
import torch

pacman100

#checking if conversion is correct

code:
import sys

import torch
from megatron import get_args, get_tokenizer, initialize_megatron, mpu
from megatron.model import GPTModel
from megatron.training import get_model
from megatron.checkpointing import load_checkpoint