ArthurZucker

from datasets import load_dataset
from trl import SFTTrainer
from peft import LoraConfig
from transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments
tokenizer = AutoTokenizer.from_pretrained("state-spaces/mamba-130m-hf")
model = AutoModelForCausalLM.from_pretrained("state-spaces/mamba-130m-hf")
dataset = load_dataset("Abirate/english_quotes", split="train")
training_args = TrainingArguments(
    output_dir="./results",
    num_train_epochs=3,

ArthurZucker

from transformers import AutoModelForCausalLM, AutoTokenizer, StaticCache
import torch
from typing import Optional
import time
import os
os.environ["TOKENIZERS_PARALLELISM"] = "1"
device = "cuda:1"
torch.set_float32_matmul_precision('high')

ArthurZucker

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)

ArthurZucker

FRANCE_ARTICLE = """<s>Marseille, France (CNN)The French prosecutor leading an investigation into the crash of Germanwings Flight 9525 insisted Wednesday that he was not aware of any video footage from on board the plane. Marseille prosecutor Brice Robin told CNN that "so far no videos were used in the crash investigation." He added, "A person who has such a video needs to immediately give it to the investigators." Robin\'s comments follow claims by two magazines, German daily Bild and French Paris Match, of a cell phone video showing the harrowing final seconds from on board Germanwings Flight 9525 as it crashed into the French Alps. All 150 on board were killed. Paris Match and Bild reported that the video was recovered from a phone at the wreckage site. The two publications described the supposed video, but did not post it on their websites. The publications said that they watched the video, which was found by a source close to the investigation. \"One can hear cries of 'My God' in several languages,\" Par

ArthurZucker

import torch 
from transformers import AutoModelForCausalLM, AutoTokenizer, StaticCache, set_seed

torch.set_printoptions(linewidth=400)

attn_implementation = "sdpa"
tokenizer = AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-chat-hf", padding_side="left", pad_token="<s>")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-chat-hf",torch_dtype=torch.bfloat16,attn_implementation=attn_implementation).to("cuda:1")
inputs = tokenizer(
    ["The best color is", "We should not undermind the issues at hand"], padding=True, return_tensors="pt"

ArthurZucker

import torch
import os
import argparse
import matplotlib.pyplot as plt
from tqdm import tqdm
from transformers import AutoModelForCausalLM, AutoTokenizer
import seaborn as sns


def get_parser():

ArthurZucker

#!/bin/bash
# conda create -n 4.29 python==3.9
# source activate 4.29
# pip install transformers==4.29.2
# pip install torch accelerate sentencepiece tokenizers colorama sacremoses googletrans

# conda create -n 4.34 python==3.9
# source activate 4.34
# pip install transformers==4.34
# pip install torch accelerate sentencepiece tokenizers colorama sacremoses googletrans

ArthurZucker

>>> from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-moe-54b")
>>> model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-moe-54b", device_map = "auto")

>>> article = "Previously, Ring's CEO, Jamie Siminoff, remarked the company started when his doorbell wasn't audible from his shop in his garage."
>>> inputs = tokenizer(article, return_tensors="pt")

>>> translated_tokens = model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id["fra_Latn"], max_length=50)
>>> tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]