Stack Overflow
Stack Overflow

Questions tagged [large-language-model]

Use this tag for questions about large language models (LLM), trained deep-learning artificial intelligence algorithms that interpret and generate natural language text.

118 questions
1
vote
1 answer

Trying to install guanaco (pip install guanaco) for a text classification model but getting error

I'm trying to install the guanaco language model https://arxiv.org/abs/2305.14314 using pip install guanaco for a text classification model but getting error. Failed to build guanaco ERROR: Could not build wheels for guanaco, which is required to…
Tamanna -
  • 41
  • 5
1
vote
1 answer

How can I run some inference on the MPT-7B language model?

I wonder how I can run some inference on the MPT-7B language model. The documentation page on MPT-7B language model  on huggingface doesn't mention how to run the inference (i.e., given a few words, predict the next few words).
Franck Dernoncourt
  • 77,520
  • 72
  • 342
  • 501
1
vote
1 answer

How to generate sentiment scores using predefined aspects with deberta-v3-base-absa-v1.1 Huggingface model?

I have a dataframe , where there is text in 1st column and predefine aspect in another column however there is no aspects defined for few text ,for example row 2. data = { 'text': [ "The camera quality of this phone is amazing.", …
Dexter1611
  • 492
  • 1
  • 4
  • 15
1
vote
0 answers

mT5 Question/Answering fine tuning is generating empty sentences during inference

mT5-small Question Answering training is converging to high accuracy, high validation accuracy, near-zero low loss; however, when testing the model on trained questions, I am always receiving empty answers. Experiment Language: Arabic Dataset used:…
Moustafa Banbouk
  • 73
  • 1
  • 5
1
vote
0 answers

Getting CUDA out of memory when calling save_pretrained in a script that tries lora training a large language model using huggingface

I am trying to train a LLama LLM ("eachadea/vicuna-13b-1.1") using LoRA on a LambdaLabs A100 40 GB. Everything seems to be working fine including the training, however the script fails on the last line:…
Ray Hulha
  • 10,701
  • 5
  • 53
  • 53
1
vote
1 answer

Is it possible to build a text classifier using existing LLM like chatgpt?

Pre LLM, when I want to build a text classifier (e.g., a sentiment analysis model, when given an input text, it returns "positive" or "neutral" or "negative"), I'll have to gather tons of data, choose a model architecture, and spend resources…
Eumaa
  • 971
  • 2
  • 15
  • 38
1
vote
1 answer

Issue with authorization with Ably when trying to run Pinecone Demo chat app

I have been trying to get the Pinecone Demo chat app in their own website up and running.Link to it. I have put all the keys properly in the .env file and the UI seems to pop up correctly. However, it shows the error: [TypeError: Cannot read…
AaravS
  • 23
  • 3
1
vote
1 answer

llama_index with LLM doing out of context answering

I am using llama_index with custom LLM. LLM I have used is open assistant Pythia model. My code : import os from llama_index import ( GPTKeywordTableIndex, SimpleDirectoryReader, LLMPredictor, ServiceContext, PromptHelper ) from…
Ankit Bansal
  • 2,162
  • 8
  • 42
  • 79
1
vote
1 answer

Problem with custom metric for custom T5 model

I have created a custom dataset and trained on it a custom T5ForConditionalGeneration model that predicts solutions to quadratic equations like this: Input: "4*x^2 + 4*x + 1" Output: D = 4 ^ 2 - 4 * 4 * 1 4 * 1 4 * 1 4 * 1 4 * 1 4 I need to get…
ALiCe P.
  • 231
  • 1
  • 10
1
vote
1 answer

How to add new tokens to an existing Huggingface tokenizer?

How to add new tokens to an existing Huggingface AutoTokenizer? Canonically, there's this tutorial from Huggingface https://huggingface.co/learn/nlp-course/chapter6/2 but it ends on the note of "quirks when using existing tokenizers". And then it…
alvas
  • 115,346
  • 109
  • 446
  • 738
1
vote
1 answer

Loading Multiple LoRA bins

I wish to fine-tune a base LLM model using LoRA with multiple datasets that are structured differently (different columns and data types). I have two questions: Can I fine-tune the model with the first dataset, then add/fine-tune the generated LoRA…
karim1104
  • 13
  • 4
1
vote
1 answer

BioGPT causal language model with unexpected error

I am trying to use a Causal Language Model from BioGPT. However, I got a strange error. Here are my steps: First, I installed transformers and sacremoses: !pip install transformers sacremoses -q Then I executed the following code: input_sequence =…
tobias
  • 501
  • 1
  • 6
  • 15
1
vote
1 answer

Databricks Dolly LLM: empty result when using LangChain with context

I'm following a tutorial on HuggingFace (let's say this one though getting same result with other Dolly models). I am trying to run predictions with context but receiving empty string as an output. I tried different models and text…
Nik
  • 161
  • 1
  • 13
1
vote
1 answer

How to use pipeline for multiple target language translations with M2M model in Huggingface?

The M2M model is trained on ~100 languages and able to translate different languages, e.g. from transformers import pipeline m2m100 = pipeline('translation', 'facebook/m2m100_418M', src_lang='en', tgt_lang="de") m2m100(["hello world", "foo…
alvas
  • 115,346
  • 109
  • 446
  • 738
1
vote
1 answer

Can mT5 model on Huggingface be used for machine translation?

The mT5 model is pretrained on the mC4 corpus, covering 101 languages: Afrikaans, Albanian, Amharic, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bulgarian, Burmese, Catalan, Cebuano, Chichewa, Chinese, Corsican, Czech, Danish,…
alvas
  • 115,346
  • 109
  • 446
  • 738
1 2
3
4 5 6 7 8