bclavie

# Fetch some text content in two different categories
from wikipediaapi import Wikipedia
wiki = Wikipedia('RAGBot/0.0', 'en')
docs = [{"text": x,
         "category": "person"}
        for x in wiki.page('Hayao_Miyazaki').text.split('\n\n')]
docs += [{"text": x,
         "category": "film"}
         for x in wiki.page('Spirited_Away').text.split('\n\n')]

hamelsmu

from fastapi import Request, HTTPException
from pydantic import BaseModel, BaseModel, HttpUrl
from modal import Secret, App, web_endpoint, Image
from typing import Optional, List
from example import proposal
import os

app = App(name="circleback", image=Image.debian_slim().pip_install("openai", "pydantic", "fastapi"))

class Attendee(BaseModel):

aksh-at

import base64
import tempfile
from typing import Optional

from pydantic import BaseModel

from modal import Image, Secret, Stub, build, enter, gpu, web_endpoint

whisper_image = (
    Image.micromamba()

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

yoavg

Reinforcement Learning for Language Models

Yoav Goldberg, April 2023.

Why RL?

With the release of the ChatGPT model and followup large language models (LLMs), there was a lot of discussion of the importance of "RLHF training", that is, "reinforcement learning from human feedback". I was puzzled for a while as to why RL (Reinforcement Learning) is better than learning from demonstrations (a.k.a supervised learning) for training language models. Shouldn't learning from demonstrations (or, in language model terminology "instruction fine tuning", learning to immitate human written answers) be sufficient? I came up with a theoretical argument that was somewhat convincing. But I came to realize there is an additional argumment which not only supports the case of RL training, but also requires it, in particular for models like ChatGPT. This additional argument is spelled out in (the first half of) a talk by John Schulman from OpenAI. This post pretty much

fscm

[macOS] Install CMake

Instructions on how to install the CMake tool on macOS.

Uninstall

First step should be to unsinstall any previous CMake installation. This step can be skipped if no CMake version was previously installed.

To uninstall any previous CMake installations use the following commands:

lovit

Huggingface

• NLP 관련 다양한 패키지를 제공하고 있으며, 특히 언어 모델 (language models) 을 학습하기 위하여 세 가지 패키지가 유용

package	note
transformers	Transformer 기반 (masked) language models 알고리즘, 기학습된 모델을 제공
tokenizers	transformers 에서 사용할 수 있는 토크나이저들을 학습/사용할 수 있는 기능 제공. transformers 와 분리된 패키지로 제공
nlp	데이터셋 및 평가 척도 (evaluation metrics) 을 제공

kzinmr

from collections import defaultdict, Counter
from operator import add
from functools import reduce
import numpy as np

from sklearn.cluster import KMeans


def dict_of_list(keys, values):
    assert(len(keys) == len(values))

kzinmr

from collections import defaultdict
from functools import reduce, partial
import numpy as np
from itertools import chain


def flatten(l):
    return list(chain.from_iterable(l))

kzinmr

"calculate PMI(A,B)=P(A,B)/P(A)P(B) for every token A and B in a window"
from itertools import tee, combinations
from collections import Counter


def count_bigram(sentence, window=5):
    # ['A','B','C','D', 'E', 'F', 'G'], 4  ->
    # [['A', 'B', 'C', 'D'],
    #  ['B', 'C', 'D', 'E'],
    #  ['C', 'D', 'E', 'F'],