All Questions
Tagged with fine-tuning artificial-intelligence
16
questions
0
votes
0
answers
24
views
Vertex AI Studio: Fine-tuned chat-bison@002 returns results are not in training data
I have a training dataset of about 1500 samples, in 1 JSONL file. I tried to fine-tune chat-bison@002 model but none of the answers in the test prompt is desired. Even when I try to copy a short ...
- 583
0
votes
1
answer
44
views
Different results for the same epoch using different number of total epochs
I am training a Machine Learning model for STS task using the Sentence Transformers library.
When I was testing it, I noticed that my model generated different results for the same number of epochs ...
0
votes
0
answers
36
views
What's the correct data structure and format to fine-tune OpenAI assistant as a vector file?
I'm trying to fine-tune an assistant that depends on gpt-3.5-turbo model with numbers and bullets but bullets never show up. I created both docx and txt files with different data format like:
Title: ...
- 2,412
0
votes
0
answers
39
views
How To Train GPT-3 On Different Datasets For Different Clients
I am planning on building an ai saas product that would focus on CRM and customer support. However, the bot should know about the company that it is answering for.
I checked their docs and did ...
- 125
0
votes
1
answer
53
views
Retrieving relevant documents for specific queries
I am trying to retrieve the top 5 relevant documents related to a user's query using the RAG-Token model. I'm using a custom knowledge base and I tried adjusting the retrieval parameters.
This is the ...
- 1
-2
votes
1
answer
44
views
Training data for chatGPT wont work correctly
I am trying to train a model in chatGPT (chatGPT-3.5-turbo-1106) for my cleaning business. based on the documentation I created and uploaded the training data successfully, but the answer I am getting ...
- 81
0
votes
0
answers
17
views
Exception has occurred. Error in accessing saved model
I recieve this error when calling my fine-tuned GPT2 saved model. Exception has occurred: OSError
Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in ...
- 1
-1
votes
1
answer
88
views
Limited Labeled Data for Fine-tuning LLMs?
Fine-tuning LLMs for specific domains is attractive, but what about scenarios with limited labeled data? Can unlabeled data or alternative approaches be effective?
Looking for insights on best ...
0
votes
0
answers
135
views
Most efficient way to fine tune SDXL for range of product
I want to fine tune SDXL using LoRA on a range of product so that SDXL can generate images of those product later on.
I have many products. What is the most efficient way to fine tune?
Do I just train ...
- 121
0
votes
1
answer
2k
views
Fine-tuning: llama-2-13b-chat
For fine-tuning of the large language models (llama2), what should be the format(.text/.json/.csv) and structure (like should be an excel or docs file or prompt and response or instruction and output) ...
- 1
0
votes
1
answer
438
views
Google Colab Free Tier: Code Stops at 51,000 Examples While Fine-tuning LLAMA 2 with Custom Dataset
I'm encountering an issue while fine-tuning Llama 2 on Google Colab using a custom dataset. The code halts exactly at 51,000 examples during the training process, even though my dataset contains 61,...
- 1
0
votes
1
answer
1k
views
I am attempting to fine-tune the stable diffusion with Dreambooth on myself (my face and body)
I am attempting to fine-tune the stable diffusion with Dreambooth on myself (my face and body), but the results are not satisfactory. I am seeking guidance on the best way to fine-tune stable ...
1
vote
0
answers
126
views
Transfer learning (or fine-tuning) pre-trained model on non-text data
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 ...
- 650
4
votes
2
answers
2k
views
What are the differences between adapter tuning and prefix tuning? [closed]
I am trying to understand the concept of adapter-tuning, prompt-tuning, and prefix-tuning in the context of few-shot learning.
It appears to me that I can apply prompt tuning to a black box language ...
- 3,041
5
votes
3
answers
8k
views
What are the differences between fine tuning and few shot learning?
I am trying to understand the concept of fine-tuning and few-shot learning.
I understand the need for fine-tuning. It is essentially tuning a pre-trained model to a specific downstream task. However, ...
- 3,041