Pinned content
View all 2 collectionsNLP admins have deemed these posts noteworthy.
Natural Language Processing FAQ
Can you answer these questions?
View all unanswered questionsThese questions still don't have an answer
Recreating Text Embeddings From An Example Dataset
Why am I seeing unused parameters in position embeddings when using relative_key in BertModel?
Is there any possibility to integrate NER and Textcat Multilabel Models in the same Pipeline
AssertionError: Unexpected kwargs: {'use_flash_attention_2': False}
BERT: how to get a quoted string as token
Looking for an extra challenge?
View all bountied questionsThese questions have a bounty on them
How to fine-tune merlinite 7B model in Python
Recommended answers
View all recommended answersThese answers have been recommended
Error while converting google flan T5 model to onnx
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 ...
Why did my fine-tuning T5-Base Model for a sequence-to-sequence task has short incomplete generation?
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: ...
How to save the LLM2Vec model as a HuggingFace PreTrainedModel object?
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 ...
Mistral model generates the same embeddings for different input texts
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&...
How to fine-tune a Mistral-7B model for machine translation?
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 ...
See what's trending
View all trending questionsThese are the most active questions in NLP Collective
How does the Google "Did you mean?" Algorithm work? [closed]
What is "entropy and information gain"?
spacy Can't find model 'en_core_web_sm' on windows 10 and Python 3.5.3 :: Anaconda custom (64-bit)
How to compute the similarity between two text documents?
googletrans stopped working with error 'NoneType' object has no attribute 'group'
Simply submit a proposal, get it approved, and publish it.
See how the process works