Stack Overflow
Stack Overflow

Questions tagged [llm]

A general tag for large language model (LLM)-related subjects. Please ALWAYS use the more specific tags if available (GPT variants, PaLM , LLaMa, BLOOM, Claude etc..)

A general tag for large language model (LLM)-related subjects. Please ALWAYS use the more specific tags if available (GPT variants, PaLM , LLaMa, BLOOM, Claude etc..)

A large language model is characterized by its large size. Their AI accellerator networks are able to process huge amounts of text data, usually scraped from the internet.

200 questions
1
vote
0 answers

how can i use 2 sources of documents as tools to a langchain agent

i have a use case where i have a csv and a text file . the csv holds the raw data and the text file explains the business process that the csv represent. i want to inject both sources as tools for a wrapper agent, that will answer the client…
user1450410
  • 191
  • 1
  • 13
1
vote
1 answer

How to get the logits of the model with a text classification pipeline from HuggingFace?

I need to use pipeline in order to get the tokenization and inference from the distilbert-base-uncased-finetuned-sst-2-english model over my dataset. My data is a list of sentences, for recreation purposes we can assume it is: texts = ["this is the…
Lucas Azevedo
  • 1,867
  • 22
  • 39
1
vote
0 answers

Error when training model with Tensorflow

I'm following this tutorial https://www.youtube.com/watch?v=V1-Hm2rNkik&list=LL&index=2 to finetune. The only difference is that i'm using the GPT2Tokenizer and GPT2LMHeadModel instead of BERT. When i get to the training part (11:53) i get the…
jam
  • 21
  • 3
1
vote
1 answer

How is the GPT's masked-self-attention is utilized on fine-tuning/inference

At training time, as far as I understand from the "Attention is all you need" paper, the way that masked-self-attention is used in the decoder is by feeding the output sequence multiple times, each time removing the mask from the next token. Q1. At…
Itamar Trainin
  • 13
  • 1
  • 5
0
votes
0 answers

Query bot on multiple JSON files on Langchain

I have around 30 GB of JSON data with multiple files, wanted build query bot on this. I have built same with text file but i am not sure how it will work for JSON data. I have explored JSONLoader but dont know how to use this to convert JSON data…
Juned Ansari
  • 5,035
  • 7
  • 56
  • 89
0
votes
0 answers

I connect llama with discord bot but doesn't work

On this code code print this error Repository Not Found for url: https://huggingface.co/api/models/llama-2-7b-chat.ggmlv3.q3_K_L.bin/revision/main. Please make sure you specified the correct repo_id and repo_type. If you are trying to access a…
Gaegeumchi
  • 1
0
votes
0 answers

How to effectively construct a data set suitable for pre-training of llm (large language models)?

I want to pre-train my own llm from scratch, so first I'm trying to construct the dataset. After several web searches and research，I get some idea from huggingface's open course: from transformers import…
JsonBorn
  • 1
  • 2
0
votes
0 answers

import SimpleDirectoryReader from llama-index

I have a conda virtual python 3.10.12 environment named LLM. I've created it on my ubuntu 18.04 LTS server. I've pip installed llama-index 0.6.9 into the virtual environment because llama-index wasn't available through conda. when I try to import…
user3476463
  • 3,967
  • 22
  • 57
  • 117
0
votes
0 answers

How to add fulltext search to llamaindex

I am making chatbot that is capable of discussing movies with langchain and llamaindex. I am following this guide. I wish llamaindex performs not only search with vector knn, but also adds some results based on direct keyword hits. Is there a way to…
Nick Zorander
  • 131
  • 12
0
votes
0 answers

How to add source doc title to each chunk of document in llamaindex

If I understand correctly how llamaindex works, it splits each long document to several smaller chunks, and then passes them as context part in LLM prompt. I am following this guide I am trying to create chatbot that is capable of discussing movies,…
Nick Zorander
  • 131
  • 12
0
votes
0 answers

Running Llama 2 on Mac using HuggingFace

I am trying to run Llama 2 model from HuggingFace. Strangely these lines work fine on Colab, but give an error on Mac. Code: from transformers import AutoTokenizer import transformers import torch model =…
Kushal Shah
  • 1
  • 1
0
votes
0 answers

How to deploy LLama on AWS Kubernetes?

I'm stuck and getting many errors such as "waiting for Auto Scaling Group" i've tried debugging via AWS but nothing seems to work - I got advised to change the plan and deployed on llama2 7b on a g5 endpoint But you need to request the g5 virtual…
marking
  • 9
  • 1
0
votes
1 answer

langchian LLM getting Serpapi error saying that the api key is invalid

I am trying to create a LLM that can use search function to get the answer of the user's questions from the internet. The current code I have is this. I have imported all the required files, so I am skipping the import…
zizon
  • 3
  • 1
0
votes
1 answer

how to assign code to a file after TextSplitter (langchain)?

i am using the RecursiveCharacterTextSplitter from Langchain to split python files. in doing so i lose the information which chunk belongs to which file. How can I keep track and assign the individual chunks to a file name afterwards? def…
alpa
  • 35
  • 3
0
votes
0 answers

open ai llm model not responding using faiss db for few iteration in the start of a conversation

I am trying to build a pdf search and chatbot engine. In the beginning of my conversation if i ask my model to provide me pdf published in year 2020 it is not responding, but asking the same question 3 4 times it start responding. What could be the…
aeshna singh
  • 1
1 2 3
…
13 14