Stay up to date
We'll highlight new content in your collectives with a blue activity indicator on navigation items and posts.
Manage preferences
Questions
Browse questions with relevant NLP tags
38,710 questions
2
votes
1
answer
46
views
Transformers LlamaForCasualLM class: base_model Attribute Mystery
Question:
I'm experiencing a question with the transformers library, specifically with the pipeline initialization. When I access the base_model attribute of a LlamaForCausalLM model, it seems to ...
- 21
0
votes
0
answers
23
views
NLTagger sentimentScore always returns 0.0 [closed]
I’m using NLTagger with the .sentimentScore tag scheme to analyze text sentiment. The setup is straightforward, and the code looks like this:
import NaturalLanguage
struct Scorer {
let tagger = ...
- 15
Advice
0
votes
1
replies
32
views
Organisation/Person tagging using Spacy
We’re working on a problem where our master dataset contains names of organizations and individuals, but some entries are untagged. We only have the names (no additional details such as email or ...
- 109
0
votes
0
answers
61
views
IndexError: index -1 is out of bounds for dimension 0 with size 0
I am currently experimenting with modifying the KV cache of the LLaVA model in order to perform controlled interventions during generation (similar to cache-steering methods in recent research). The ...
0
votes
0
answers
32
views
Inconsistent name normalization when extracting data using OpenAI API (gpt-4.0-mini)
I'm using the OpenAI API (gpt-4.0-mini) to extract and normalize names from social media posts.
However, even with strict prompting, the output sometimes contains slightly different spellings for the ...
1
vote
0
answers
119
views
Transformers 'could not import module pipeline' to jupyter notebook
I need to to run a series of pre-trained fine-tuned models from Hugging Face to Jupyter notebook. I have updated to the latest version of both PyTorch and Transformers, but when I run the code
from ...
1
vote
1
answer
69
views
Xcode Can't Find swift-transformers Package
I'm trying to implement Speech-to-Text transcription in my Swift app using Hugging Face's swift-transformers package to run Whisper models locally.
I've added the package to my Xcode project, but when ...
- 425
1
vote
1
answer
96
views
Memory usage keeps increasing when extracting embeddings via sentence-transformers
I have a set of about 100M paragraph-sized strings (multilingual) I am extracting embeddings for, but the memory usage keeps increasing until I start overflowing into disk swap:
model = ...
- 1,076
0
votes
1
answer
68
views
Generating response with KV Cached System Prompt throws error when Input Tokens are less than Prompt Tokens
I am trying to run Mistral-7B-Instruct-v0.2.
Each run is PROMPT + details[i].
PROMPT has instructions on how to generate JSON based on details.
As the prefix part of each input is same; kind of like a ...
1
vote
1
answer
57
views
Output of for loop filling down in dataframe instead of returning corresponding values for each row
I'm using SpaCy to process a series of sentences and return the five most common words in each sentence. My goal is to store the output of that frequency analysis (using Counter) in a column beside ...
- 23
0
votes
0
answers
82
views
Transformers with Python 3.12.3 produce lots of errors
I got Python 3.12.3 on an Ubuntu server. I tried to install transformers, tokenizers, datasets and accelerate to use the Seq2SeqTrainer in the transformers.
I used a virtual environment for the ...
- 54.4k
0
votes
0
answers
85
views
Torch example transformer with TransformerDecoder
In the torch example provided here https://github.com/pytorch/examples/tree/main/word_language_model, tansformer only uses torch.TransformerEncoder and torch.TransformerDecoder is overwritten with a ...
- 1,395
0
votes
0
answers
31
views
T5-small generates only padding tokens during validation/test in PyTorch Lightning
I'm fine-tuning T5-small using PyTorch Lightning and encountering a strange issue during validation and test steps.
The Problem:
During validation_step and test_step, model.generate() consistently ...
- 21
3
votes
0
answers
109
views
How does one log the operations done on a GPU during the execution of Python code?
I have encountered a particular problem while executing a function from the transformers library of huggingface on an Intel GPU wheel of torch. Since I am doing something I normally shouldn't be ...
0
votes
0
answers
62
views
Utilizing GPU with RNN models which takes it's output as input [torch]
I have a machine-translation model. In this model, I calculate a vector for a given sentence and I take this vector, aggregate with each generated output of RNN and put it into RNN again for ...
- 1,395
1
vote
0
answers
67
views
How to pass P_map: dict[str, torch.Tensor] to PEFT (LoRA)?
My proxy goal is to change LoRA from h = (W +BA)x to h = (W + BAP)x. Preliminary code attached for your reference
My actual goal is to train a model with the following loss: 〖Θ ̃=(arg min)┬Δ ̂ 〗〖‖𝑓_(...
- 2,193
1
vote
2
answers
157
views
How to fix “Expected all tensors to be on the same device” when running inference with Qwen3-VL-4B-Instruct?
I am trying to run the code example for run some inference on the model Qwen/Qwen3-VL-4B-Instruct model:
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
# default: Load the ...
- 84.7k
0
votes
0
answers
66
views
Streamlit app throwing "NotFittedError: idf vector is not fitted" even though TF-IDF pipeline is fitted and works locally
I trained a sentiment classification model using a scikit-learn Pipeline that includes a TfidfVectorizer and LogisticRegression classifier.
Everything works perfectly on my local machine, but when I ...
0
votes
0
answers
47
views
Training data format for SpanCategorizer when using custom suggester function
I'm taking a stab at building my own claim extraction pipeline (first time spaCy user).
Upstream in my pipeline, I feed n amount of docs to NER in the en_core_web_sm pretrained model in order to ...
2
votes
1
answer
60
views
Angle Embedder in Python Messing Up Logging Config
I wrote another question on this earlier, but could not pinpoint the issue on my side, here, I am giving a minimal reproducible code.
System
Angle version 0.5.6
UV 0.8.22
Python 3.12
Ubuntu 24.04
I ...
- 1,730
1
vote
0
answers
52
views
Transformer model outputs degrade after ONNX export — what could be causing this?
I’ve exported a fine-tuned BERT-based QA model to ONNX for faster inference, but I’m noticing that the predictions from the ONNX model are consistently less accurate than those from the original ...
- 41
-1
votes
2
answers
74
views
LangChain HuggingFace ChatHuggingFace raises StopIteration with any model
I’m trying to use LangChain’s Hugging Face integration to chat with the model TinyLlama/TinyLlama-1.1B-Chat-v1.0 for the very first time, but I’m getting a StopIteration error when calling .invoke().
...
- 51
9
votes
2
answers
2k
views
RemoteEntryNotFoundError with downloading models from Hugging Face in Kaggle
Recently i have started to get some strange errors, for example RemoteEntryNotFoundError: 404 Client Error. (Request ID: Root=1-68e82630-293b962044bc3e6c1453ec73;43987a97-e033-4590-951e-829a3c87d2cb) ...
0
votes
0
answers
55
views
ONNX Runtime Helsinki-NLP in Java
has anyone managed to translate something using Helsinki-NLP and ONNX Runtime in Java? Using a Python script, I generated these files:
├── encoder_model.onnx
├── decoder_model.onnx
├── ...
- 393
3
votes
2
answers
184
views
Multimodal embedding requires video first, then image - why?
I am working with OmniEmbed model (https://huggingface.co/Tevatron/OmniEmbed-v0.1), which is built on Qwen2.5 7B. My goal is to get a multimodal embedding for images and videos. I have the following ...
- 76
-1
votes
1
answer
58
views
How to reconstruct sentences from mean-pooled embeddings (embedding inversion) [closed]
I’m working on a research problem where I want to reconstruct or paraphrase sentences starting from synthetic embeddings.
The embeddings are global (mean-pooled), not token-level, so they lose ...
0
votes
0
answers
51
views
Training with spaCy from command line, don't know why gpu-id not recognized
I am having the hardest of times getting my training session to use my gpu 0 which by every measure is present and correctly setup with cuda 12.2.
When I try to do python -m spacy train base_config....
- 9,764
1
vote
1
answer
117
views
How to make Microsoft Presidio detect and mask Indian names and unusual text patterns in banking data?
I’m working on anonymizing PII in banking text using Microsoft Presidio
.
The built-in PERSON recognizer (which uses spaCy under the hood) works for some Western names and when the sentence is clear
...
- 11
0
votes
0
answers
78
views
How to solve device mismatch issue when using offloading with QwenImageEditPlus pipeline and GGUF weights
After failing to make the QwenImageEditPlus run (https://huggingface.co/spaces/discord-community/README/discussions/9#68d260e32053323e6bfab30c), I tried a different approach (thanks to all the example ...
- 1,215
0
votes
0
answers
97
views
pippy examples: torch._dynamo.exc.UserError: It looks like one of the outputs with type <class transformers.cache_utils.DynamicCache> is not supported
when the program starts to initialize pipeline object, a unexpected error was thrown:
[rank0]: Traceback (most recent call last):
[rank0]: File "/root/anaconda3/envs/polar/lib/python3.12/site-...
- 1
2
votes
1
answer
89
views
How to integrate a lightweight image-to-text model into a React Native app?
I am trying to integrate an image-to-text model into a React Native mobile app.
My requirements:
The model should support image + text input → text output.
It should be lightweight enough to run on ...
- 11
-2
votes
1
answer
151
views
I need a Python implementation of my Longest Possible Common Subsequence (LPCS) algorithm [closed]
Please be merciful - I've never asked a question here (I've answered a few) and am a total Python noob.
I developed an algorithm in SQL Server to compute the Longest Possible Common Subsequence (LPCS) ...
- 8,008
2
votes
1
answer
76
views
How can I extract symptoms/diseases from a running transcription?
I'm working on a project where I'm attempting to extract medical symptoms from a running transcription. I'm using SocketIO to get mic audio and then using Whisper to transcribe the audio into text ...
2
votes
1
answer
143
views
RuntimeError: Expected all tensors to be on the same device when using local HuggingFace model in LangChain Agent
I'm building a simple agent using LangChain that leverages a locally-hosted HuggingFace model (gpt-oss-20b). I'm using the transformers pipeline and wrapping it in LangChain's HuggingFacePipeline.
The ...
- 194
3
votes
0
answers
52
views
Azure ML Endpoint Fails with HFValidationError even after using pathlib.Path
I am trying to deploy a fine-tuned Mistral-7B model on an Azure ML Online Endpoint. The deployment repeatedly fails during the init() phase of the scoring script with an huggingface_hub.errors....
- 157
0
votes
1
answer
80
views
PermissionError: [Errno 13] Permission denied: 'Qwen3-0.6B-SFT'
I am getting the following error when running training, using the TRL library in the following HuggingFace space: vishaljoshi24/trl-4-dnd.
My SDK is Docker and as far as I'm aware there are not ...
-1
votes
1
answer
466
views
ModuleNotFoundError for transformers.pipeline after installing PyTorch for CUDA
I'm a bit stumped on an issue that just popped up. My code, which uses the transformers library, was running perfectly fine until I tried to install a CUDA-compatible version of PyTorch.
Everything ...
- 194
1
vote
1
answer
90
views
KeyError: 'Cache only has 0 layers, attempted to access layer with index 0'
raise KeyError(f"Cache only has {len(self)} layers, attempted to access layer with index {layer_idx}")
KeyError: 'Cache only has 0 layers, attempted to access layer with index 0'
When I try ...
- 11
0
votes
0
answers
207
views
Cannot import `QwenForCausalLM` after installing `v4.51.3-Qwen2.5-Omni-preview` tag; pip installs 4.52.0.dev0 instead
Description:
I am trying to install the Hugging Face Transformers version that supports the Qwen2.5-Omni model. According to the official docs, the correct tag to install is v4.51.3-Qwen2.5-Omni-...
1
vote
0
answers
61
views
ValueError when resuming LoRA fine-tuning with sentence-transformers CrossEncoderTrainer: "Unrecognized model" error
I'm fine-tuning a CrossEncoder model with LoRA using sentence-transformers library on Kaggle (12-hour limit). I need to resume training from a checkpoint, but I'm getting a ValueError when trying to ...
0
votes
0
answers
56
views
How do I compute validation loss for a fine-tuned Qwen model in Hugging Face Transformers during evaluation?
I trained a Qwen model on my own dataset. Now I need to evaluate my trained model using the loss function, but I don’t know how to do it. I saw examples for other metrics such as accuracy and ...
0
votes
0
answers
252
views
ModuleNotFoundError: 'triton.ops' when loading 4-bit quantized model with bitsandbytes on Kaggle
I have this code:
import os
import torch
from datasets import Dataset
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
TrainingArguments,
)
from peft ...
- 1
1
vote
2
answers
360
views
How can I match the token count used by BGE-M3 embedding model before embedding?
For my particular project, it would be very helpful to know how many tokens the BGE-M3 embedding model would break a string down into before I embed the text. I could embed the string and count the ...
2
votes
0
answers
89
views
How to Run an Open-Source 20B Model locally? [closed]
I have gpt oss 20b model's weights locally.
What are the necessary steps to run a 20B model using transformers.
in files that I downloaded is multi safetensor files. and also a .bin file.
which one of ...
- 21
2
votes
1
answer
102
views
How to stop hugging face pipeline operation
I need to stop hugging face pipeline operation. I tried to achieve this using a method from the following question, but it didn't work. I set the breakpoint on the line return flag and expected ...
- 412
0
votes
0
answers
154
views
optuna, huggingface-transformers: RuntimeError, "Tensor.item() cannot be called on meta tensors" when n_jobs > 1
I'm trying to use optuna to find good hyperparameters for a fine-tuning task I'm doing with some different language models. My actual code is more complex, but here's a MWE:
import torch
import optuna
...
- 449
0
votes
0
answers
49
views
The data type of the llava model uncontrollably changes to float32
I am using the llama-8b-llava model. I have made some modifications to the model, which are non-structural and do not introduce any parameters. During the model loading process, I used the torch....
- 23
0
votes
0
answers
139
views
Convert SentencePiece tokenizer to ONNX
I'm developing (Python) an FAQ system based on embeddings to perform similarity queries between a user's question and the FAQ knowledge base. The FAQ needs to run on Android smartphones.
I'm using the ...
- 177
0
votes
1
answer
88
views
How do I create a Pytorch Dataset from multiple files where each file has multiple batches
How do I create an dataset that reads in data from multiple files, but where each file has lots of rows or batches.
For example, I have a partitioned parquet dataset (created with pandas.to_parquet), ...
- 3,840
1
vote
2
answers
87
views
how to efficiently use spacy for pos tagging and ner
I am having 200 documents and I want to do NER and pos_tagging. However I find spacy to be too slow(I am running this code in google colab):
for doc in nlp.pipe(dataset["text"], batch_size=...
- 737
cronoik
scored 10
answering questions this week
Members can contribute articles
Simply submit a proposal, get it approved, and publish it.
See how the process works
Simply submit a proposal, get it approved, and publish it.
See how the process works