Nahid Alam nahidalam

## normcore-llm.md

      
              1 file
            
          
              330 forks
            
          
                67 comments
              
            
              3439 stars
            
          
                veekaybee
                / normcore-llm.md
            
            
              Last active
              December 7, 2025 16:13
            
              
                Normcore LLM Reads
              
          
    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


## universal_sentence_encoder_featurizer.py
""" Enhancing Intent Classification with the Universal Sentence Encoder:
https://medium.com/scalableminds/enhancing-intent-classification-with-the-universal-sentence-encoder-ecbcd7a3005c
"""

from rasa_nlu.featurizers import Featurizer

import tensorflow_hub as hub
import tensorflow as tf


## download_glue_data.py
''' Script for downloading all GLUE data.

Note: for legal reasons, we are unable to host MRPC.
You can either use the version hosted by the SentEval team, which is already tokenized,
or you can download the original data from (https://download.microsoft.com/download/D/4/6/D46FF87A-F6B9-4252-AA8B-3604ED519838/MSRParaphraseCorpus.msi) and extract the data from it manually.
For Windows users, you can run the .msi file. For Mac and Linux users, consider an external library such as 'cabextract' (see below for an example).
You should then rename and place specific files in a folder (see below for an example).

mkdir MRPC
cabextract MSRParaphraseCorpus.msi -d MRPC

## ner.py
# https://nlpforhackers.io/named-entity-extraction/

import os
import string
import collections
import pickle
from collections import Iterable

from nltk.tag import ClassifierBasedTagger
from nltk.chunk import ChunkParserI, conlltags2tree, tree2conlltags

## keras_gensim_embeddings.py
from __future__ import print_function

import json
import os
import numpy as np

from gensim.models import Word2Vec
from gensim.utils import simple_preprocess
from keras.engine import Input
from keras.layers import Embedding, merge
	""" Enhancing Intent Classification with the Universal Sentence Encoder:
	https://medium.com/scalableminds/enhancing-intent-classification-with-the-universal-sentence-encoder-ecbcd7a3005c
	"""

	from rasa_nlu.featurizers import Featurizer

	import tensorflow_hub as hub
	import tensorflow as tf
	''' Script for downloading all GLUE data.

	Note: for legal reasons, we are unable to host MRPC.
	You can either use the version hosted by the SentEval team, which is already tokenized,
	or you can download the original data from (https://download.microsoft.com/download/D/4/6/D46FF87A-F6B9-4252-AA8B-3604ED519838/MSRParaphraseCorpus.msi) and extract the data from it manually.
	For Windows users, you can run the .msi file. For Mac and Linux users, consider an external library such as 'cabextract' (see below for an example).
	You should then rename and place specific files in a folder (see below for an example).

	mkdir MRPC
	cabextract MSRParaphraseCorpus.msi -d MRPC
	# https://nlpforhackers.io/named-entity-extraction/

	import os
	import string
	import collections
	import pickle
	from collections import Iterable

	from nltk.tag import ClassifierBasedTagger
	from nltk.chunk import ChunkParserI, conlltags2tree, tree2conlltags
	from __future__ import print_function

	import json
	import os
	import numpy as np

	from gensim.models import Word2Vec
	from gensim.utils import simple_preprocess
	from keras.engine import Input
	from keras.layers import Embedding, merge