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

jasonjmcghee

from abc import ABC
from typing import List, Optional, Any

import chromadb
from langchain.docstore.document import Document
from langchain.embeddings.base import Embeddings
from langchain.vectorstores import Chroma


class CachedChroma(Chroma, ABC):

tuulos

from metaflow import FlowSpec, step, IncludeFile

def dataset_wine():
    from sklearn import datasets
    return datasets.load_wine(return_X_y=True)
    
def model_knn(train_data, train_labels):
    from sklearn.neighbors import KNeighborsClassifier
    model = KNeighborsClassifier()
    model.fit(train_data, train_labels)

anythinggraphic

.responsive-nav-icon::before,
.responsive-nav-close::before {
    color: #93a748;
    content: "\f0c9";
    font-family: FontAwesome;
    font-size: 22px;
    position: relative;
}

.responsive-nav-close::before {

9cardinals

# principal amount

p = 10_000

# annual rate of interest
r = 0.05

# number of years
t = 5