Artificial Intelligence Stack Exchange

0 votes

0 answers

15 views

Prefix tuning in LLM uses learnable vectors to fine tune the model

jackson

1

asked 23 hours ago

1 vote

1 answer

65 views

How does a multidimensional vector get fed into a single node in a neural network?

CommunityBot

1

modified yesterday

1 vote

3 answers

62 views

Would maximizing (instead of minimizing) error of an LLM/HMM lead to complex behavior?

BigMistake

113

answered yesterday

2 votes

1 answer

141 views

How would the probability of a document $P(d)$ be computed in the Naive Bayes classifier?

CommunityBot

1

modified Nov 23 at 16:04

0 votes

2 answers

679 views

Does it make sense to add an additional attention layer while fine-tuning Bert?

CommunityBot

1

modified Nov 20 at 22:06

1 vote

1 answer

45 views

NLP "small" model to improve "big" model

Neil Slater

30.2k

modified Nov 20 at 13:46

7 votes

2 answers

5k views

How to resolve lexical ambiguity in natural language processing?

Mithical♦

2,885

modified Nov 20 at 10:44

1 vote

1 answer

87 views

Masking in Decoder of Transformer

Cesar Ruiz

453

answered Nov 19 at 5:37

1 vote

0 answers

19 views

What is the input to an encoder-decoder transformer in next word prediction task?

mehsheenman

111

asked Nov 13 at 21:27

0 votes

1 answer

34 views

Setting number of rows returned by vector stores

CommunityBot

1

modified Nov 13 at 20:03

2 votes

2 answers

1k views

How does a LLM (transformer) pick words from its vocabulary?

CommunityBot

1

modified Nov 13 at 15:01

2 votes

2 answers

291 views

How do LSTM and GRU avoid to overcome the vanishing gradient problem?

CommunityBot

1

modified Nov 13 at 11:01

2 votes

1 answer

976 views

If GPT-3 is trained on predicting the next token, how is it able to take commands?

CommunityBot

1

modified Nov 13 at 10:03

6 votes

2 answers

391 views

How does GPT-based language model like ChatGPT determine the n-th letter of a word?

Jakub Podolak

46

answered Nov 11 at 9:34

Stack Exchange Network

Explore our questions

Prefix tuning in LLM uses learnable vectors to fine tune the model

How does a multidimensional vector get fed into a single node in a neural network?

Would maximizing (instead of minimizing) error of an LLM/HMM lead to complex behavior?

How would the probability of a document $P(d)$ be computed in the Naive Bayes classifier?

Does it make sense to add an additional attention layer while fine-tuning Bert?

NLP "small" model to improve "big" model

How to resolve lexical ambiguity in natural language processing?

Masking in Decoder of Transformer

What is the input to an encoder-decoder transformer in next word prediction task?

Setting number of rows returned by vector stores

How does a LLM (transformer) pick words from its vocabulary?

How do LSTM and GRU avoid to overcome the vanishing gradient problem?

If GPT-3 is trained on predicting the next token, how is it able to take commands?

How does GPT-based language model like ChatGPT determine the n-th letter of a word?

Hot Network Questions