Questions tagged [language-model]
Language models are used extensively in Natural Language Processing (NLP) and are probability distributions over a sequence of words or terms.
158 questions
0
votes
0
answers
54
views
How much improvement does OpenAI o1 achieve from the chain of thought?
https://openai.com/index/learning-to-reason-with-llms/
OpenAI o1 also add more data than the last version of LLM.
- 711
0
votes
0
answers
47
views
For image+text, how is pre-training of Multimodal LLM generally done?
For image+text without video, how is pre-training of Multimodal Large Language Model generally done?
Choice-1: Transform image to text, and then input all the text to LLM?
Choice-2: Transform image to ...
- 711
0
votes
0
answers
27
views
Generating transaction data for a dataset to train on
My project is to predict what payment option a customer might use depending on various factors on a checkout screen.
For example here are some of the fields I would have
Variables : User_Location ...
0
votes
0
answers
9
views
What are the key quality metrics for large language model releases?
I am a first year PhD student working on improving the release practices of Machine Learning Models, especially pre-trained large language models. I want to understand the above concept for a ...
0
votes
0
answers
11
views
What is query generation re-ranking method?
I am reading up on reranking methodologies that leverage LLMs. Relevant literature.
One of the methods suggested is query generation
Or, the same methodology from another source
The task is to rank ...
- 903
0
votes
0
answers
19
views
How to find out that a conversation with a chatbot is likely ended
I'm working on a ChatBot with Python and langchain, and I'd like to have a metric that I could use to understand how close we ...
1
vote
1
answer
60
views
Callback handlers in Langchain
This might be an odd question, but why is there two codes for the class BaseCallbackHandler?
https://api.python.langchain.com/en/latest/_modules/langchain_core/callbacks/base.html#BaseCallbackHandler
...
0
votes
0
answers
60
views
How is a causal language model correctly fine-tuned?
I want to fine-tune an SLM like Phi-2 through the huggingface API. I am in doubt how to achieve that, because I see two ways to do that and I am wondering which is the correct way.
The task is just a ...
- 113
0
votes
0
answers
79
views
Converting relational database into vector database
Is there any open-source tools for converting relational database to vector database to be used in llm applications? Which steps can be taken in the conversion?
- 37
0
votes
0
answers
26
views
What is system prompt in fine tuning of GPT3.5 for natural language to sql queries
What exactly is a system prompt while finetuning GPT3.5 or a language model in general? How can I build system prompt for the task of converting natural language to SQL queries
- 37
0
votes
0
answers
21
views
what is the main difference between ROUGE and BLUE?
Both (ROUGE, BLUE) are useful to find the similarity between machine generated summary and reference summary.
what is the main difference?
- 43
0
votes
1
answer
38
views
What languages llama2 supports?
Which languages llama2 supports? I looked at the docs and huggingface but I couldn't find a list. Just it says usage in other languages than English as out-of-scope.
- 37
0
votes
1
answer
44
views
How can I get the list of pretrained large language models?
Is there any place I can get the list of pre-trained large language models in a neat way? Despite the most common ones like gpt, BARD, llama2, which llm do you suggest that can be used for RAG and ...
- 37
0
votes
1
answer
62
views
How to check the license of a LLM for specific use?
How to check if a large language model has a license allowing to fine tune the model and then publish it publicly? How can I be sure that I can use and fine-tune a large language model without ...
- 37
0
votes
2
answers
43
views
How to choose ideal pretrained model for fine-tuning?
I started to work with LLMs lately and want to know how people choose their pre-trained models in their fine-tuning tasks? What is the criteria to choose the base model and which factors affect?
- 37
0
votes
0
answers
92
views
Can I fine tune MedPaLM model
Is it possible to fine-tune MedPaLM and MedPaLM2; Google's llms trained using PaLM specialized for medical domain. Can we fine-tune these models further to get more specialized models?
- 37
0
votes
1
answer
43
views
Is Machine Reading Comprehension (MRC) outdated?
I recently went through some litterature about knowledge-enhanced language models and found connections with the Machine Reading Comprehension (MRC) task. However, I couldn't find papers more recent ...
- 109
1
vote
1
answer
536
views
How can I leverage machine learning for log analysis?
I am new to data science and trying to find possibilities of using datascience in tasks. I have a set of logs which I want to convert to json. The logs are more or less of same format and I can write ...
- 111
0
votes
1
answer
160
views
Purely extractive Language Model
Given an email thread, I am trying to extract the body of the most recent email.
I used to do that with rules. Now I am testing Large Language Models (LLM) to see if I they provide a less ad hoc ...
- 103
0
votes
1
answer
203
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’...
- 121
0
votes
1
answer
318
views
What is the input to an encoder-decoder transformer in next word prediction task?
I'm trying to understand how encoder-decoder architectures are used, or if they are used at all, for generative tasks that do not require an explicit prompt (ie. machine translation, summarization, ...
- 103
1
vote
1
answer
2k
views
Why is 0.7, in general, the default value of temperature for LLMs?
I have recently read through a lot of documentation and articles about Large Language Models (LLMs), and I have come to the conclusion that 0.7 is, most of the time, the default value for the ...
- 11
0
votes
0
answers
27
views
TFRobertaSequenceClassification for Address Normalization task
I have dataset with two column: one with faulty addresses, and other with correct addresses. I want to train a model such that, I can use it later for correcting all the incoming faulty addresses.
I ...
0
votes
0
answers
1k
views
How to read CSV File into Vector Store
I have a CSV file, and I am using langchain to read it into the vector store FAISS. My question is, since I have a CSV file, is RecursiveTextSplitter required? Put differently, consider the following ...
- 49
0
votes
1
answer
22
views
Locating base.py when working on Colab
I have faced an error while working with langchain on colab. There is a post on github which recommends changing some configurations in
...
- 103
0
votes
1
answer
98
views
Why do we want to maximize the average log probability in neural language models?
I am currently trying to understand the Paragraph Vector framework by reading the paper "Distributed Representation of Sentences and Documents" by Quoc Le and Thomas Mikolov but I have ...
- 1
1
vote
2
answers
722
views
What is source_column argument in csv loader?
In this tutorial, what is the purpose of source_column argument? Does it act like a primary key in Databases? Thanks in advance.
...
- 49
1
vote
1
answer
287
views
Why is Spacy sentiment score 0.0 for a sentence?
I'm trying to get a sentence's sentiment score using Spacy and apparently every sentence I pass gets a score of 0.0. Can someone help me understand what's going wrong here?
...
- 27
1
vote
0
answers
36
views
"text" parameter in pinecone call from langchain
In this tutorial, I do not understand what "text" refers to
vectorstore = Pinecone(index, embeddings.embed_query, "text")
Could you please help?...
- 49
-3
votes
1
answer
96
views
coversational AI chatbot using langchain and chatgpt 3.5?
can we develop end to end hotel booking coversational AI chatbot using langchain and chatgpt 3.5 ?
2
votes
1
answer
571
views
Implementation of spBLEU
I was looking for a way to explore evaluation metrics for language translation models and I came across spBLEU. I can’t find any implementations/examples that would help me start. Does anyone have a ...
- 33
9
votes
3
answers
17k
views
Why does everyone use BERT in research instead of LLAMA or GPT or PaLM, etc?
It could be that I'm misunderstanding the problems space and the iterations of LLAMA, GPT, and PaLM are all based on BERT like many language models are, but every time I see a new paper in improving ...
- 193
0
votes
1
answer
66
views
How quickly can a transformer self-heal if you wipe out one of its layers?
Say we have a fully-trained N-layer transformer model (encoder-only, decoder-only, or encoder-decoder), with embedding dimension ...
- 1,244
2
votes
1
answer
57
views
Smart Selection of Training Data for Fine-tuning Language Models in Small Domains
Background
I am working to make language models (for example, Stanford's Alpaca model) perform well on a new small domain through fine-tuning on domain-specific dataset $D$.
If the size of $D$ is $N$, ...
- 93
0
votes
1
answer
2k
views
memory and context in LLM models
I have a large document and I may need to introduce a large part of it to my llm for insight generation I know that that text can be chunked into parts and with the right prompt I can get what I want ...
- 137
3
votes
1
answer
3k
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 ...
7
votes
3
answers
5k
views
Further Training a pre-trained LLM
My goal is to use the general knowledge and language understanding of a pre-trained LLM and to continue training on a smaller domain specific corpus to improve the model's knowledge on the domain. ...
- 101
3
votes
1
answer
2k
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 ...
- 33
1
vote
1
answer
104
views
How can models like Mosaic's MPT-7b or Bloombergs BLOOMGPT take in so many tokens?
I've read the paper on ALiBi, and I understand that these models are biasing the values made in the query/key multiplication.
But from my understanding, when I build the actual model I give it ...
- 113
1
vote
1
answer
329
views
LLM powered chat bot enhanced by NER
I have been reading on the capabilities of LLM based conversational agents and have been wondering if there is even possibility for any further enhancement with the addition of NER to such system.
If ...
0
votes
1
answer
162
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 ...
- 101
0
votes
1
answer
77
views
Easy question on autoregressive LLM
For LLM decoder, how exactly is the K, Q, V for each decoding step?
Say my input prompt is "today is a" (good day).
At t= 0 (generation step 0):
K, Q, V are the projections of the sequence (&...
- 123
3
votes
1
answer
468
views
Were any LLMs trained on Google books?
An important limiting factor on the performance of large language models, is the amount of training text available. Of course, using e.g. the Gutenberg archive of public domain books is an obvious ...
- 159
0
votes
1
answer
272
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 ...
- 105
3
votes
1
answer
2k
views
What is purpose of stacking N=6 blocks of encoder and decoder in transformer?
I was trying to understand transformer architecture from "Attention is all you need" paper.
What is purpose of stacking $N=6$ blocks of encoder and decoder? Does higher blocks represent ...
- 219
1
vote
1
answer
167
views
What does it exactly mean by "different representation subspaces" in transformer?
I was trying to understand transformer architecture from "Attention is all you need" paper.
The paper says:
Multi-head attention allows the model to jointly attend to information from ...
- 219
1
vote
1
answer
386
views
How K and V are extracted from encoder output in transformer?
I was trying to understand transformer architecture from "Attention is all you need" paper. The paper shows following transformer architecture:
How $K$ and $V$ is extracted from $512$ ...
- 219
1
vote
1
answer
1k
views
Understanding dimensions of vectors at various places in transformer architecture
I was trying to understand transformer architecture from "Attention is all you need" paper. It says following regarding dimensions of different vectors:
The input consists of queries and ...
- 219
1
vote
2
answers
1k
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 ...
- 11
2
votes
1
answer
493
views
dolly v2 - how does it internally learn to follow instructions
this is more a curiosity query than anything else. The git repo for dolly gives us an easy way to swap, the training dataset , to train custom models, as long as we follow the format. I however have ...
- 342