buttercutter

# [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://arxiv.org/abs/2312.00752)

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, Dataset
from torch.nn import functional as F
from einops import rearrange, repeat
from tqdm import tqdm

veekaybee

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

HarshTrivedi

import torch
from torch import LongTensor
from torch.nn import Embedding, LSTM
from torch.autograd import Variable
from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence

## We want to run LSTM on a batch of 3 character sequences ['long_str', 'tiny', 'medium']
#
#     Step 1: Construct Vocabulary
#     Step 2: Load indexed data (list of instances, where each instance is list of character indices)

miguelmota

package server

import (
	"bufio"
	"fmt"
	"log"
	"net"
)

// Server ...

aparrish

karpathy

"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)