Frequently asked questions relating to NLP. Many of these may be questions that are often asked over and over, duplicates would likely be closed in favor of these. Add the best answer (using the ...

Berthold♦

answered Aug 2, 2023 at 17:43

Can you answer these questions?

View all unanswered questions

These questions still don't have an answer

0 votes

0 answers

6 views

How to use HuggingFace's run_translation.py script to train a translation from scratch?

I tried various HuggingFace scripts to build language models, such as run_mlm.py (link), run_clm.py (link) and run_translation.py (link). For the former 2 scripts, it can train a language model from ...

Raptor

53.7k

asked 7 hours ago

0 votes

0 answers

9 views

Training LLM uses unexpected amount of GPU memory

I'm training model with self-implemented training loops. A 1.5B Qwen2 occupies 40G of GPU memory. When I did the same training using llama factory, it only takes about 24G. I tried to delete some ...

StaEx_G

asked 12 hours ago

0 votes

0 answers

17 views

How to evaluate LLM response

I am retrieving response using QWEN 72B model. I want to validate my response and don’t have ground truth answers. How can I evaluate my response without help of ground truth answers. I want to use ...

CommunityBot

modified 7 hours ago

0 votes

0 answers

10 views

what kind of pre-processing is required to apply on sentence before passing it dependency parser?

I'm trying out sentiment analysis where I convert the sentence into a Graph with nodes being word embedding and edges being dependency between the two words. I'm still confused how exactly should I ...

Harsh Chauhan

asked 15 hours ago

0 votes

0 answers

17 views

Finetuning BERT on classification task, tensor device mismatch error

I'm having trouble on fine-tuning a BERT model on a classification task, as I'm quite new to this. My data is composed of two columns, "item_title" (my input) and "meta_categ_id" (...

talonmies

71.8k

modified yesterday

Looking for an extra challenge?

View all bountied questions

These questions have a bounty on them

2 votes

1 answer

40 views

+100

Saving Fine-tune Falcon HuggingFace LLM Model

I'm trying to save my model so it won't need to re-download the base model every time I want to use it but nothing seems to work for me, I would love your help with it. The following parameters are ...

Johnny Cheesecutter

1,782

answered yesterday

Recommended answers

View all recommended answers

These answers have been recommended

1 vote

1 answer

159 views

Error while converting google flan T5 model to onnx

I am looking to convert flan-T5 model downloaded from Hugging face into onnx format and make inference with the same. My input data is the symptoms of disease and expected output is the Disease name ...

alvas

120k

answered May 15 at 15:44

Answer

Use https://huggingface.co/datasets/bakks/flan-t5-onnx instead. And to convert the google/flan-t5, see https://huggingface.co/datasets/bakks/flan-t5-onnx/blob/main/exportt5.py from pathlib import ...

View answer

alvas

120k

answered May 15 at 15:44

1 vote

1 answer

81 views

Why did my fine-tuning T5-Base Model for a sequence-to-sequence task has short incomplete generation?

I am trying to fine-tune a t5-base model for creating appropriate question against a compliance item. Compliance iteams are paragraph of texts and my question are in the past format of them. I have ...

alvas

120k

modified May 8 at 17:17

Answer

Because of: labels = tokenizer(targets, max_length=32, padding="max_length", truncation=True) Most probably your model has learnt to just output/generate outputs that are ~32 tokens. Try: ...

View answer

alvas

120k

answered May 8 at 17:16

1 vote

1 answer

160 views

How to save the LLM2Vec model as a HuggingFace PreTrainedModel object?

Typically, we should be able to save a merged base + PEFT model, like this: import torch from transformers import AutoTokenizer, AutoModel, AutoConfig from peft import PeftModel # Loading base MNTP ...

alvas

120k

answered Apr 12 at 18:33

Answer

Wrapping the LLM2Vec object around like in https://stackoverflow.com/a/74109727/610569 We can try this: import torch.nn as nn from transformers import PreTrainedModel, PretrainedConfig from ...

View answer

alvas

120k

answered Apr 12 at 18:33

3 votes

1 answer

509 views

Mistral model generates the same embeddings for different input texts

I am using pre-trained LLM to generate a representative embedding for an input text. But it is wired that the output embeddings are all the same regardless of different input texts. The codes: from ...

alvas

120k

answered Apr 11 at 12:13

Answer Accepted

You're not slicing it the dimensions right at outputs.last_hidden_state[0, 0, :].numpy() Q: What is the 0th token in all inputs? A: Beginning of sentence token (BOS) Q: So that's the "embeddings&...

View answer

alvas

120k

answered Apr 11 at 12:13

4 votes

1 answer

707 views

How to fine-tune a Mistral-7B model for machine translation?

There's a lot of tutorials online that uses raw text affix with arcane syntax to indicate document boundary and accessed through Huggingface datasets.Dataset object through the text key. E.g. from ...

ghost21blade

modified Mar 24 at 5:23

Answer

The key is to re-format the data from a traditional machine translation dataset that splits the source and target text and piece them up together in a format that the model expects. For the Mistral 7B ...

View answer

alvas

120k

answered Mar 13 at 20:56

See what's trending

View all trending questions

These are the most active questions in NLP Collective

467 votes

18 answers

103k views

How does the Google "Did you mean?" Algorithm work? [closed]

I've been developing an internal website for a portfolio management tool. There is a lot of text data, company names etc. I've been really impressed with some search engines ability to very quickly ...

CommunityBot

modified May 10, 2018 at 20:23

354 votes

7 answers

219k views

What is "entropy and information gain"?

I am reading this book (NLTK) and it is confusing. Entropy is defined as: Entropy is the sum of the probability of each label times the log probability of that same label How can I apply ...

Waseem Ahmad Naeem

answered Aug 1, 2018 at 17:26

160 votes

34 answers

425k views

spacy Can't find model 'en_core_web_sm' on windows 10 and Python 3.5.3 :: Anaconda custom (64-bit)

what is difference between spacy.load('en_core_web_sm') and spacy.load('en')? This link explains different model sizes. But i am still not clear how spacy.load('en_core_web_sm') and spacy.load('en') ...

Dipesh Paul

answered Sep 19, 2023 at 10:25

284 votes

14 answers

304k views

How to compute the similarity between two text documents?

I am looking at working on an NLP project, in any programming language (though Python will be my preference). I want to take two documents and determine how similar they are.

Milad

answered Aug 28, 2023 at 5:26

216 votes

18 answers

223k views

googletrans stopped working with error 'NoneType' object has no attribute 'group'

I was trying googletrans and it was working quite well. Since this morning I started getting below error. I went through multiple posts from stackoverflow and other sites and found probably my ip is ...

Amir Charkhi

modified Mar 23, 2023 at 7:49

Collectives on Stack Overflow: a subcommunity defined by tags to help you find trusted answers faster and share knowledge with the community.

Get started with collectives

Explore collective features

Read your first bulletin

Check out the leaderboard

Learn about the different roles

Discover recommended answers

See all collectives

AVERAGE RESPONSE RATE (within 24 hours)

17%

Help improve the percentage by Answering questions

LEADERBOARD POSITION

View all 16 tags

Collectives™ on Stack Overflow

NLP Collective

Pinned content

Can you answer these questions?

Looking for an extra challenge?

Recommended answers

See what's trending