Questions tagged [huggingface]
The huggingface tag has no usage guidance.
95
questions
0
votes
0
answers
23
views
Fine-tuning Hugging Face’s Llama Model with Unlabelled Data from PDFs from niche domain
I’m unsure about the next steps. Specifically, I have the following questions:
How can I prepare my unlabelled data for the fine-tuning process?
What’s the best way to fine-tune the Llama model with ...
0
votes
0
answers
16
views
What happens when I set is_decoder to True in the bert API from huggingface?
Please help me understand the implications of initialising the bert model from huggingface with is_decoder parameter set to True
...
0
votes
1
answer
58
views
Open-Source Large Language Models (LLM): Your experience and recommendation
I’m looking for an open-source LLM for a new project. I want to use it for instructions and to fine-tune the model to a specific domain like legal and rights. Some LLMs are open-source, but they didn’...
0
votes
0
answers
11
views
F1 and Exact-Match (EM) Score in Extractive QA NLP
I have a question as to how the F1 should be calculated in NLP and whether the text normalization is optional or not.
So I have been working on a project where we created a closed-domain extractive QA ...
0
votes
0
answers
30
views
How to use Bertweet model for topic modeling
The problem is implementation of Bertweet in a topic-modeling project with understandable output like BERTopic, i want to use it on a relatively large (20k tweets) unlabelled dataset to segment it ...
0
votes
0
answers
217
views
How to get Llama-2 Rotary Embeddings?
I want to get the Llama-2 rotary embeddings. I do print(model) and get the following output:
In the picture I highlight the rotary embeddings.
How can get the ...
0
votes
0
answers
17
views
Errors in results after saving model vs using directly from memory
I am trying to save a Fine Tuned model using trainer.save_model() but after I load the saved_model it just responds with the input back again and does not give any ...
0
votes
0
answers
50
views
Specifying arguments of HuggingFaceHub
In this tutorial, when specifying
llm = HuggingFaceHub(
repo_id=repo_id, model_kwargs={"temperature": 0.5, "max_length": 64})
only ...
0
votes
1
answer
140
views
How to Use Multiple Adapters with a Pretrained Model in Hugging Face Transformers for Inference?
I have a pretrained Llama-2 model in the models_hf directory and two fine-tuned adapters: a summarization adapter in ...
1
vote
0
answers
47
views
Deploying a model with GPU and pay-per-inference
I may have the wrong stack exchange. If that's the case, could someone point me to a stack that could help with this. Anyways...
My backend employs a sentence transformer model from HuggingFace. Since ...
0
votes
0
answers
17
views
How can BERT/Transformer models accept input batches of different sizes?
I understand that all inputs in a batch need to be of the same size. However, it seems BERT/Transformers models can accept batches with different sizes as input.
How is that possible? I thought we ...
0
votes
0
answers
10
views
Create samples out of documents for Causal Language Modelling
I want to create an input source for Causal Language model using Llama 2 model in hugging face. I have a set of documents which are scraped from a specific website and want to fine-tune on them. Each ...
0
votes
0
answers
290
views
Adapting a BERT-based model from HuggingFace for NER (named entity recognition) and RE (relation extraction)?
Context: NER (named entity recognition) and RE (relation extraction) from sentences obtained from radiology reports (medical text).
There is a BERT-based model from HuggingFace I would like to use for ...
0
votes
0
answers
17
views
Decoder model selection for sequence-to-sequence ASR with XLS-R
I am new to building models for Speech ASR. I want to build a model for Speech Transcription in Urdu. I used XLS-R (following the example by Patric von Platen on Huggingface Colab notebook. My ...
0
votes
0
answers
117
views
Fine-Tune Llama on main and auxiliary task
I am trying to fine-tune Llama model on two task at the same time, using hugging face library:
Main task: Causal language model like the model was initially trained for
A classification task based on ...
0
votes
1
answer
667
views
Can I run falcon-7b on a free google colab?
I'm a beginner at ML and AI.
Background:
I wanted to try out falcon-7b, the example I'm trying out: https://colab.research.google.com/drive/1BiQiw31DT7-cDp1-0ySXvvhzqomTdI-o?usp=sharing (Falcon-...
0
votes
0
answers
17
views
Sentiment extraction with hugging face ready to use model
I have a set of reviews for which I need to extract their sentiments and use those sentiments as an independent variable in an econometric model. I used one of the ready-to-use models of hugging face ...
0
votes
0
answers
35
views
Which language model to use for this use case? [Finetuning on custom dataset]
An example from my train data is as follows:
...
0
votes
0
answers
149
views
Multiple CSV files input for hugging face table question-answering in Python
I am trying to write a code in HuggingFace Python to input multiple CSV files and feed them to the tokenizer for table question-answering. If I were to input only one CSV file, the code would look ...
0
votes
0
answers
12
views
Large Language model for regression on urls
I am trying to fit a BERT model for a URL regression task. I have a URL as a feature and I have to predict a metric M for it. Keeping a learning rate like $10^{-5}$, the model is overfitting in about ...
0
votes
0
answers
122
views
How to load Hugginface model on CPU?
My system runs out of memory on GPU. But I want just to test if it works and want to load it on CPU. How do I do that?
Adding device = torch.device(‘cpu’) before ...
0
votes
0
answers
17
views
"Probabilistic" One-Hot-Encoder for transformers library
I'm using the transformers library to fine-tune a LLM for classification.
However, my problem is a bit particular, as the labels are hierarchical, that is, in the form A-1, A-2, B-1, B-2 etc.
...
1
vote
1
answer
103
views
How can someone evaluate llama index model?
I have built a openAI llama index based model which takes multiple pdf and able to give chatbot based response. I want to evaluate the llm for accuracy. I already know method such as Rouge and Bleu. ...
3
votes
1
answer
1k
views
LMM Fine Tuning - Supervised Fine Tuning Trainer (SFTTrainer) vs transformers Trainer
When should one opt for the Supervised Fine Tuning Trainer (SFTTrainer) instead of the regular Transformers Trainer when it comes to instruction fine-tuning for Language Models (LLMs)? From what I ...
0
votes
0
answers
54
views
What is exactly the difference between Huggingface, MLserver and seldon core?
Kind of a newbie to practical ML development.
As far as I can understand, huggingface provides packaged, ready to deploy, pre trained ML models, whereas MLserver and seldon core are used to actually ...
1
vote
0
answers
735
views
Fine-tuning a pre-trained LLM for question-answering
Objective
My goal is to fine-tune a pre-trained LLM on a dataset about Manchester United's (MU's) 2021/22 season (they had a poor season). I want to be able to prompt the fine-tuned model with ...
0
votes
0
answers
24
views
Extremely silly transformers fine-tuning doubt
Suppose say I have a TFT5ConditionalGenration model instantiated with tensor flow.
When you do model.fit, the model will pass the inputs in a feed-forward way similar to a call method. The model will ...
1
vote
0
answers
166
views
How to monitor training of text generation models?
I'm finetuning a pretrained Huggingface model based on Transformers for a downstream Text Generation task, but I have doubts on how the fine-tuning process should be monitored:
In classification, I ...
0
votes
1
answer
135
views
Can we train the Dolly v-2 model on a large general purpose unlabelled text?
I am familiar with ML and Deep Learning concepts and have had a look at Dolly and even got the pretrained model running on a Jupyter lab notebook on Databricks.
However when I take a look at their ...
0
votes
0
answers
22
views
Huggingface not saving model checkpoint
I am trying to train T5 model. This is how my training arguments look like:
...
0
votes
0
answers
684
views
Creating LLM chatbot using llama-index + langchain
As the title suggests: I'm trying to build a chatbot which his goal should be sort of like "chatgpt".
The chatbot will be installed on Slack workspace and I'm struggling with which scope I ...
1
vote
0
answers
74
views
trainable weights in automodel and comparison with lora
if i use RobertaForSequenceClassification or AutoModelForSequenceClassification,
are all the weights trained or only the new classification head trained
also ,
i am also noticing for "roberta-...
0
votes
0
answers
71
views
Question about GPT-2 causal masking for downstream tuning
I'm currently finetuning a pre-trained GPT-2 model for image captioning. Using a ViT for image encoding, the output embeddings are then fed into the GPT-2 model (from HuggingFace) as ...
0
votes
1
answer
219
views
Passing target text to gpt2 and T5 for fine tuning to learn text generation task
I have text with each line in following format:
<text-1> some text-1 <text-2> some text-2 <text-3> some text-3
I want fine tune model to learn ...
1
vote
2
answers
763
views
Fine-tuned MLM based RoBERTa not improving performance
We have lots of domain-specific data (200M+ data points, each document having ~100 to ~500 words) and we wanted to have a domain-specific LM.
We took some sample data points (2M+) & fine-tuned ...
0
votes
0
answers
192
views
Fine tune Flan T5 to build a SlackBot
I want to create a Slack chatbot that will be able to "somehow" mock a "ChatGPT like" behavior.
I want the bot to be able:
answer questions
understand from context
summarize info
...
2
votes
2
answers
1k
views
Dynamic batching and padding batches for NLP in deep learning libraries
This is the usual way we train modern deep learning models for NLP, e.g. with Huggingface libraries where we have a fix length for the input no. of tokens/subwoords unit. https://huggingface.co/docs/...
0
votes
0
answers
833
views
RuntimeError: It looks like your LightningModule has parameters that were not used in producing the loss returned by training_step
I'm trying to use donut, which is a transformer model with a huggingface implementation, and pre-train it on a language it hasn't been yet on my desktop. Unfortunately the version of the stack ...
0
votes
2
answers
67
views
Fine-tune GPT on sketch data (stroke-3)
These past days I have started a personal project where I would like to build a model that, given an uncompleted sketch, it can finish it.
I was planning on using some pretrained models that are ...
0
votes
0
answers
210
views
How to finetune a closed generative huggingface model?
I want to finetune a huggingface pretrained model on our internal documentation in a way it stats answering related questions. I could not find the adequate tutorial.
0
votes
0
answers
52
views
Which decoder method is used with “facebook/wav2vec2-base-960h”?
When using wav2vec2:
facebook/wav2vec2-base-960h
Which decoder method is used when running
processor.decode ?
Naive Decoding or Beam Search or Language Model ?
How can I see it on the ...
0
votes
0
answers
11
views
Which zero-shot models predict the contents of an image?
I'm looking for the class of machine learning models on Hugging Face where you provide an image and a list of options and it returns which of those options appear in the image for example I might ...
0
votes
0
answers
15
views
When using wav2vec2 inference, does the quantitation being used?
According to wav2vec model:
it seems that quantitation only used on training phase (in order to train the transformer layer to quantitative the data to use small number of discrete values).
So my ...
0
votes
0
answers
144
views
is the distilRoberta transformer model overfitting or underfitting?
I am a bit new to ML, below are the results after I fine tuned distilRoBERTa using HuggingFace Trainer. I cant tell if my model is over-fitting, under-fitting or ok? I ran 7 epochs.
I think its ...
0
votes
0
answers
738
views
How to deal with DataCollator and DataLoaders in Huggingface?
I have issues combining a DataLoader and DataCollator. The following code with DataCollatorWithPadding results in a ...
0
votes
1
answer
51
views
error useing soft max gives outputs greater than 1
I am using Hugging Face AutoModelForSequenceClassification, model is roberta, using it for text classification.
There are 3 classes.
The output is: ...
0
votes
3
answers
678
views
Combining sentence embeddings of two different models (sBERT and mBERT)
I am working on a chatbot that helps students.
So, I wanted to make use of bert model which has better performance on mathematics, which lead to me to math-bert, but the paper on it said that it was ...
0
votes
1
answer
127
views
Possible NLP approaches to extract 'goals' from text
I am planning to take up an interesting NLP project. I want to extract 'goal' statements from lengthy reports. For example, the goals can be We would be reducing our carbon footprint by 50% by 2025 or ...
0
votes
1
answer
173
views
Extract the embedding from a specific layer of MarianModel
I am using using MarianModel from the hub of HuggingFace for a translation task. Now I want to extract the embedding from the output of the last MarianEncoderLayer ...
1
vote
1
answer
68
views
What could cause pre-trained Opus-MT models have wildly varying inference time when being used with transformers library?
I have been testing pre-trained Opus-MT models ported to transformers library for python implementation. Specifically, I am using opus-mt-en-fr for English to French translation. And the tokenizer and ...