Questions tagged [finetuning]
The finetuning tag has no usage guidance.
72
questions
0
votes
0
answers
17
views
Can LLM fine-tuning be used to improve a language?
I'm Danish, and with all the excitement around open LLM models, I'm feeling a little left out.
Take Llama 2, for example - it was trained on a very small Danish dataset. Just enough to learn the words ...
- 101
0
votes
0
answers
9
views
How does supervised fine-tuning work in InstructGPT?
See Figure 2 from the InstructGPT paper:
I want to know how Step 1 works. Here is one possible algorithm.
Pass the prompt through the model, and compute the negative log of the probability of the ...
- 125
0
votes
0
answers
52
views
Fine-tuning LLM with limited documents and hierarchy
Hello LLM enthusiasts.
I am wondering w.r.t. a neighbouring project if there are state of the art approaches to fine tune a model if:
the realm of documents is limited (still more than just a few),
...
- 1
0
votes
0
answers
103
views
Finetune LLM model on tabular data
Is it possible or even recommended to finetune LLMs such as llama2 on tabular data?
I have a csv with historical gold buy prices.
...
- 101
1
vote
1
answer
403
views
Understanding alpha parameter tuning in LORA paper
I was reading the LORA paper https://arxiv.org/pdf/2106.09685.pdf a thing I don’t understand is section 4.1, where the updates are updated by alpha, where alpha is a constant in r. It is said that ...
- 11
0
votes
0
answers
281
views
Unsupervised fine tuning of Code LLMs
How to prepare code data to fine tune a code LLM in an unsupervised way or is it even possible?
For example:
Task: Code summarization with custom code base (with no summaries)
Let's assume that this ...
- 1
0
votes
0
answers
35
views
Fine tuning a pretrained model gives worse results
I have a pretrained model for multi-class activity classification. I also have a dataset D which is similar to the dataset used to train the pretrained model.
When I run data from D through the ...
0
votes
0
answers
23
views
What is the input and output of GPT model for fine-tuning?
From my understanding, for the pretraining of GPT model, we need to do next token prediction task.
In this case,
Input -> The GPT models are general-purpose language models that can perform ... (...
- 1
0
votes
0
answers
34
views
Which language model to use for this use case? [Finetuning on custom dataset]
An example from my train data is as follows:
...
- 101
0
votes
0
answers
10
views
Add parameter efficient training in retrieval natural language processing
I am studying some paper with retrieval augmented generation and parameter efficient work on NLP task, ex: adapter, prefix tuning, prompt ...
I wonder that can I get better performance with parameter-...
- 23
2
votes
1
answer
697
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
97
views
Fine-Tuning / Transfer learning results in worse performance
My task is creating a model for QA-purposes.
I have only ~200 samples on a specific domain of questions.
Using a pretrained like DeBERTa without any further changes results in f1 scores of ~35%.
To ...
0
votes
1
answer
17
views
Can I add a new output class to a decoder and train only the final layer?
I am wondering how to approach a project, where I would like to increase the number of output classes of an already trained network. I have very good reason to believe that the model has already ...
- 123
1
vote
0
answers
632
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 ...
- 13
0
votes
0
answers
475
views
Easyocr Fine tune english_g2.pth text recognition model using my custom dataset
Am using easy OCR from the link below
https://github.com/JaidedAI/EasyOCR
I have custom dataset of 25000 images for training and 1000 images for validation in all_data folder generated. Max image ...
0
votes
0
answers
172
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
...
- 199
0
votes
0
answers
17
views
Multimodal classification - multiple images for each record
I have a multimodal classification task. In my dataset, each record consists of
a text
a list of 1 to 4 associated images
a label
Probably, I'd want to use transformers encoders to represent both ...
2
votes
0
answers
1k
views
What is zero-shot vs one-short vs few-shot learning?
Are there any papers/research work that deals with generalizing the matrix of how the *-shot(s) learning are defined?
There's a wide variety of papers that titled ...
- 2,340
0
votes
2
answers
63
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 ...
- 31
1
vote
1
answer
417
views
How to limit a GPT chatbot in specific domain?
When we are going to fine-tune a GPT-3 model for Q&A in specific domain, how we can avoid it to answer the questions from the other domains?
Suppose out chatbot is to answer to questions from ...
- 263
0
votes
0
answers
11
views
Model only surpass the baseline in a certain fine-tuning condition
I am training an vanilla 5-layers LSTM. My task is trying to compare two models (baseline and compared model) between without and with the additional features. However, I found out that the compared ...
0
votes
0
answers
166
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.
- 131
0
votes
0
answers
133
views
Finetuning fasttext with unlabeled text corpus
I am training a classifier which is supposed to take the name of a product as input. For this purpose I want to finetune a pre-existing fasttext model on my article names.
My code looks like this
<...
2
votes
1
answer
180
views
Does GPT-3 remember data from prompts used to fine tune it?
I am trying to fine tune a model using OpenAI's fine tuning API. I am passing bodies of text (for example, news paper articles) as prompts and the data I want from it as completions.
Let us consider ...
0
votes
0
answers
114
views
How to fine-tune a large language model for translation in a multi-dataset setting?
The Problem
We need to translate from language N to language C. If it helps, N is a natural ...
0
votes
0
answers
31
views
Training an Object Detection Model from scratch vs. pretrained weights
I have a question related to training a object detection model:
Lets say I have trained a model for detecting 1 class with, say, 500 images including positive and negative samples and saved the best ...
- 1
0
votes
0
answers
27
views
Help to find strategy of transfer learning with a conditional pix2pix model
so I trained a similar model to pix2pix GAN to generate output images. I condition my model on three different types:
there are 120 input images and 2 parameters (param_1, param_2). For each parameter,...
- 1
0
votes
0
answers
19
views
BERT model improvement approach - general advice
I'm new to machine learning and trying to improve an nlp / BERT model. I'd like to know if there is a way to improve my results by inspecting the weights and attention of individual words and phrases.
...
- 101
2
votes
0
answers
914
views
How many samples in dataset are required to fine-tune BERT for binary classification?
I'm trying to fine-tune a BERT-based model for a binary classification task (data is in English). The dataset I'm working with is quite small (~500 samples, out of which 80% are currently used for ...
- 21
0
votes
0
answers
21
views
Transfer learning (or fine-tuning) pre-trained model on non-text data (PyTorch)
I am currently fine-tuning a sentiment analysis bert-based model using PyTorch Trainer from hugging face. So far, so good.
I have easily managed to fine-tune the model on my text data. However, I'd ...
- 101
0
votes
0
answers
131
views
How to find the optimal number of samples for fine-tuning a pre-trained language model for text classification?
I'm trying to fine-tune a pre-trained language model (PLM) for text classification. The dataset that I'm using for fine-tuning includes about 40k samples.
I wonder if I should use the whole dataset or ...
- 115
1
vote
1
answer
59
views
Training a CNN in production on new data
How should I approach training a convolutional neural network in production on new data when I detect model performance degradation due to data or concept drift? Resources like this one and this one ...
1
vote
0
answers
536
views
Fine Tune GPT-3 without prompt?
I was wondering if it's possible to fine tune GPT-3 without using the "prompt" and "completion" method as shown in the documentation. More specifically, I want to fine tune a GPT-3 ...
- 11
0
votes
0
answers
48
views
How to add few-shot to the prompt when finetuning a language model?
I want to finetune GPT2 to extract relevant data from a given text. So for (a trivial) example, given the text "the car was manufactured in X, can reach Y km/h, and has Z horse powers", my ...
- 137
0
votes
1
answer
37
views
About improving the classifier when using a pre-trained model
I have tried adding a layer in the Resnet Model as shown:
...
- 181
1
vote
1
answer
220
views
How to further fine-tune a transformer NLP model on domain specific dataset, after general fine-tuning
I would like to fine-tune a pre-trained BERT-like model for a semantic similarity analysis task in the fashion of the SNLI/MNLI task (i.e. classify sentence pairs to "entailment" or "...
- 81
1
vote
1
answer
53
views
Fine tuning Convolutional Neural Network with a learnable first layer
I have a classification task using grayscale images and I want to leverage from pretrained networks.
There are a lot of resources out there presenting how to fine tune large neural nets like resnet, ...
- 65
0
votes
0
answers
51
views
Parameters for training a sentence-similarity model using Bert?
I have a list of sentences :
sentences = ["Missing Plate", "Plate not found"]
I am trying to find the most similar sentences in the list by ...
1
vote
2
answers
111
views
How can I fine tune a model to detect digits, used to detect denominations of currency notes
So the task at hand is to detect the denomination of any currency banknote. The dataset I have is about 2k images of each denomination (12 in total). An example banknote (after noise removal, erosion ,...
1
vote
0
answers
201
views
Is it possible to "fine-tune" a pre-trained logistic regression model?
Fine tuning is a concept commonly used in deep learning. We may have a pre-trained model and then fine-tune it to our specific task.
Does that apply to simple models, such as logistic regression?
For ...
- 111
0
votes
0
answers
1k
views
ValueError: Mixed precision training with AMP or APEX (`--fp16` or `--bf16`) and half precision evaluation (`--fp16) can only be used on CUDA devices
i’m fine tuning the wav2vec-xlsr model. i’ve created a virtual env for that and i’ve installed cuda 11.0 and tensorflow-gpu==2.5.0 but it gives the following error : ValueError: Mixed precision ...
1
vote
1
answer
177
views
Pretrained vs. finetuned model
I have a doubt regarding terminology. When dealing with huggingface transformer models, I often read about "using pretrained models for classification" vs. "fine-tuning a pretrained ...
- 289
1
vote
1
answer
544
views
Is it okay to fine-tuning bert with large context for sequence classification?
I want to create sequence classification bert model. The input of model will be 2 sentence. But i want to fine tuning the model with large context data which consists of multiple sentences(which ...
- 11
1
vote
1
answer
23
views
Tuning model by my metric
My project is using a metric to evaluate the performance of regression model, it is not belong to basic metric in Machine learning (MSE,MAE,...).
So, how can I tuning model base on my metric ?
- 21
0
votes
1
answer
23
views
Are most deep learning models online learning models?
I'm online learning starter. from my perspective, online learning model is the model which can update its paramater with data flows(I've seen a article pointing out that incremental model is ...
- 1
0
votes
1
answer
25
views
Transformer similarity fine-tuned way too often predicts pairs as similar
I fine-tuned a transformer for classification to compute similarity between names. This is a toy example for the training data:
...
- 101
0
votes
0
answers
84
views
Value accuracy remains the same
I have used my own build model and also fine-tuned other two model ResNeT50 and VGG16, but val_acc remains the same for them all.
...
- 21
0
votes
0
answers
91
views
Where to download the weights for PyTorch Efficientnet-b6
I would like to know how to download the weights for PyTorch Efficientnet-b6 architecture. Only the weights, not the entire architecture.
- 695
0
votes
1
answer
2k
views
How to freeze certain layers in models obtained from keras.applications
I am currrently trainning to use transfer learning on ResNet152 obtained from Keras Applications:
...
- 7
0
votes
0
answers
520
views
How to fine-tune GPT-J with small dataset
Firstly, thank you so much for looking at this post. I could really use some help.
I have followed this guide as closely as possible: https://github.com/kingoflolz/mesh-transformer-jax
I'm trying to ...
- 101