The huggingface tag can be used for all libraries made by Hugging Face. Please ALWAYS use the more specific tags; huggingface-transformers, huggingface-tokenizers, huggingface-datasets if your question concerns one of those libraries.
Questions tagged [huggingface]
606 questions
2
votes
0 answers
SentencePiece tokenizer encodes to unknown token
I am using HuggigFace implementation of SentencePiece tokenizer, i.e., SentencePieceBPETokenizer and SentencePieceUnigramTokenizer classes. I train these tokenizers on dataset which has no unicode characters and then try to encode the string that…
Shital Shah
- 63,284
- 17
- 238
- 185
2
votes
0 answers
call huggingface tokenizer in c#
I would like to call huggingface tokenizer in C# and wonder what might be the best way to achieve this. Specifically, I'd like to use mt5 tokenizer for CJK languages in C#.
I have seen certain nuget packages developed such as BertTokenizer in C#,…
exteral
- 991
- 2
- 12
- 33
2
votes
1 answer
Finetuning Open LLMs
I am a newbie trying to learn fine tuning. Started with falcon 7B instruct LLM as my base LLM and want to fine tune this with open assistant instruct dataset. I have 2080 Ti with 11G VRAM. So I am using 4 bit quantization and Lora.
These are the…
codemugal
- 81
- 1
- 1
- 4
2
votes
2 answers
AttributeError: 'AcceleratorState' object has no attribute 'distributed_type'
import transformers
from datasets import load_dataset
import tensorflow as tf
tokenizer = transformers.AutoTokenizer.from_pretrained('roberta-base')
df = load_dataset('csv', data_files={'train':'FinalDatasetTrain.csv',…
Amr Samer
- 21
- 1
2
votes
0 answers
How to finetune an LLM model on your own codebase?
I have 10 code repositories in Javascript (VueJS) (Each repository corresponds to 1 Theme)
I want to train an LLM model on these 10 code repositories so that I can generate new themes using prompts.
The LLM model take the context of 10 code…
Aadesh
- 403
- 3
- 13
2
votes
1 answer
Look for good ways to prepare customized dataset for training controlnet with huggingface diffusers
I want to personally train the controlnet, but I find it inconvenient to prepare the datasets. As I follow the huggingface tutorial available at this link: https://huggingface.co/blog/train-your-controlnet, I believe I should organize the dataset in…
Yun
- 21
- 2
2
votes
1 answer
How to use HuggingFace Inference endpoints for both tokenization and inference?
I am trying to set up separate endpoints for tokenization and inference using HuggingFace models. Ideally I would like to use HuggingFace inference endpoints.
Is there a straightforward way to spin up endpoints for encoding, decoding, and inference…
Steven Krawczyk
- 21
- 1
2
votes
1 answer
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 questions such as "How can MU improve?", or "What are…
Tom Bomer
- 83
- 7
2
votes
1 answer
Stable Diffusion Webui ConnectTimeoutError while starting
I'm trying to set up stable diffusion on a server so that users can access it via RDP and generate what they need. The server in place I hosted on-premise and doesn't have any internet connection. I installed all needed libs via whl files. I was…
Sacul0815
- 21
- 2
2
votes
1 answer
Huggingface - Pipeline with a fine-tuned pre-trained model errors
I have a pre-trained model from facebook/bart-large-mnli I used the Trainer in order to train it on my own dataset.
model = BartForSequenceClassification.from_pretrained("facebook/bart-large-mnli", num_labels=14, ignore_mismatched_sizes=True)
And…
Dolev Mitz
- 103
- 14
2
votes
0 answers
How to use huggingface + gradio API in javascript
I'm going over the fastai ML course and got stuck in the second lesson with a minor problem - a classifier app that works fine on huggingface spaces doesn't get called correctly by a script suggested by the course team. Here's the code:
Having…
Non-chemist_dude
- 53
- 2
2
votes
1 answer
What is the function of the `text_target` parameter in Huggingface's `AutoTokenizer`?
I'm following the guide here: https://huggingface.co/docs/transformers/v4.28.1/tasks/summarization
There is one line in the guide like this:
labels = tokenizer(text_target=examples["summary"], max_length=128, truncation=True)
I don't understand the…
Betty
- 512
- 7
- 19
2
votes
1 answer
Export MarianMT model to ONNX
I would like to use the Helsinki-NLP/opus-mt-de-en model from HuggingFace to translate text.
This works fine with the HuggingFace Inference API or a Transformers pipeline, e.g.:
from transformers import AutoTokenizer, pipeline
from…
RGe
- 1,181
- 1
- 10
- 19
2
votes
0 answers
Huggingface - time out or connection error
I want to use LLaMA and OPT via the Hugging Face API. However, I always get the same two error messages. Either
ConnectionError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))
Or
{'error': 'Model…
Frigoooo
- 51
- 4
2
votes
1 answer
validation loss shows 'no log' during fine-tuning model
I'm finetuning QA models from hugging face pretrained models using huggingface Trainer, during the training process, the validation loss doesn't show. My compute_metrices function returns accuracy and f1 score, which doesn't show in the log as…
Leran Zhang
- 21
- 1