1,020 questions
-1
votes
0
answers
21
views
I'm having an Error on hugging face and nothing is working
I'm trying to deploy a project on huggingface but there is an error that I can't seem to solve.
I'm getting this error
Cannot start Node server on any port in the range 9001-9001.
Please install Node ...
-1
votes
0
answers
28
views
Msty AI: Download Models from Huggin Face [closed]
I would like to install some models from huggin face on Msty but there are so many model choices. How do i know if i am downloading the right one or if i need to download multiple of the files for it ...
-1
votes
0
answers
22
views
PDF parsing "MinerU" for layout analysis, may lost equations. Lead to RAG incorrect answers [closed]
The Retrieval-Augmented Generation (RAG) data pre-processing using "MinerU" for PDF parsing.
I noticed that some equations are lost layouts in markdown result (like the .png (1) and (3) ...
- 1
-1
votes
1
answer
31
views
LLM for journaling chatbot [closed]
I am trying to create a chatbot to help one with introspection and journaling for a school project. I essentially want it to be able to summarize a response and ask questions back in a way that uses ...
0
votes
0
answers
62
views
TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType. Huggingface model locally
I'm trying to run a LM locally I don't really have much knowledge of huggingface.
What I did is creating account there then creating a token that can read/write.
I created a project did pip install ...
- 328
-1
votes
0
answers
19
views
How to use validation dataset in LLaVa
I want to log my model's accuracy after each epoch and its final accuracy at the end but I cannot find a simple way of doing this.
I am following this tutorial: https://console.brev.dev/launchable/...
0
votes
1
answer
18
views
How to force langchain to use HF_DATA environment variable to load the model from local disk instead of Internet
How to force langchain to use HF_DATA environment variable to load the model.
The Snowflake/snowflake-arctic-embed-l model files have been downloaded to $HF_HOME/Snowflake/snowflake-arctic-embed-l.
$ ...
- 22.4k
-2
votes
0
answers
14
views
Simple error: Hugging Face Dockerfile Specific , directory error
# ✅ Step 1: Use a lightweight Python image
FROM python:3.10-slim
# ✅ Step 2: Create a non-root user for better security
RUN useradd -m -u 1000 user
# ✅ Step 3: Install Git (needed for cloning)
...
-1
votes
0
answers
35
views
Cannot import name 'DiffusionPipeline' from 'pipelines'
I want to run the following code on colab.
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(...
- 1
-1
votes
0
answers
13
views
Source code hugging face audio widget / recommendations audio plug in
Does anyone know where to get the source code for the audio widgets that are used in the hugging face space?
Example: https://huggingface.co/spaces/styletts2/styletts2
Or can you recommend a good js ...
1
vote
1
answer
34
views
Where is the HuggingFace model saved in when loading a model on colab?
I have this code for loading a generative model. I'm not sure how to see model files in colab (i.e., config.json etc.).
model_id = "deepseek-ai/DeepSeek-R1-Distill-Llama-8B"
pipeline = ...
- 503
-1
votes
0
answers
26
views
Implementing custom huggingface pipeline that uses non pytorch/tesnorflow model
this is my very first post on stackoverflow. I have used it many times but never really asked anything. Now however, I run into an issue that I really cant solve and would really really appreciate ...
-1
votes
0
answers
51
views
Error when installing autotrain-advanced Python library on Sagemaker AI
I'm trying to install the autotrain-advanced Python library to train ollama Llama model in Sagemaker AI, but I'm getting an error.
This is my sagemaker instance configs:
instance type: ml.g4dn....
-1
votes
0
answers
32
views
What is the encoding format used to store BPE byte sequences in HuggingFace Tokenizers?
Consider the first 256 tokens from the vocabulary of HuggingFace GPT-2 BPE Tokenizer:
"vocab": {
"!": 0,
"\"": 1,
"#": 2,
"$&...
- 1,239
-1
votes
0
answers
42
views
How to get statistics/history huggingface datasets?
In python, I can use huggingface dataset like;
dataset = load_dataset("mlabonne/FineTome-100k", split='train')
The question is, I'd like to get the dataset's statistics like no. of columns, ...
- 654
0
votes
0
answers
38
views
LangChain: 'dict' object has no attribute 'replace' when using Chroma retriever
I am working on a chatbot using LangChain, ChromaDB, and Hugging Face models. However, when I try to run my script, I get the following error:
import os
import dotenv
from langchain.prompts ...
-1
votes
1
answer
42
views
Is there a change in the langchain libraries and interfaces?
Is there a change in the langchain libraries and interfaces ?
Of late I am seeing that sample code in langchain documentation is not working. Hence my question.
For example, the below code throws an ...
0
votes
0
answers
26
views
Getting Unicode error while saving to disk in distiset
Here is my code
import argparse
import os
from typing import List
from pydantic import BaseModel, Field
from datasets import Dataset
from dotenv import load_dotenv
from distilabel.llms import ...
0
votes
0
answers
15
views
Problems with pretraining models using huggingface
When I went to run a demo using hugging face's pre-trained model HumanVLM, there was a KeyError: 'llava' problem, the demo was as follows. And I have downloaded the pre-trained model locally in the ...
- 1
5
votes
2
answers
2k
views
Why does HuggingFace-provided Deepseek code result in an 'Unknown quantization type' error?
I am using this code from huggingface:
This code is directly pasted from the HuggingFace website's page on deepseek and is supposed to be plug-and-play code:
from transformers import pipeline
...
0
votes
1
answer
169
views
How to fix Index put requires the source and destination dtypes match` with `google/gemma-2-2b` in Transformers?
I’m trying to train a language model using google/gemma-2-2b with the Hugging Face Transformers Trainer. The same training script works fine for other models like gpt2 and meta-llama/Meta-Llama-3-8B, ...
- 5,237
-1
votes
0
answers
25
views
Errors while deploying jina clip v2 - trust_remote_code
I'm trying to deploy jina-clip v2 on sagemaker (using huggingface, not jumpstart). I've tried to find examples on how to do it, but I haven't been able to find anything for jina-clip. Below is my code:...
- 9
0
votes
1
answer
54
views
Image segmentation ONNX from huggingface produces very diferent results when used in ML.Net
I have been trying to get an image segmentation model from huggingface (RMBG-2.0) to work for inference using ML.NET. After a lot of trial and error, I finally got the code to compile and produce an ...
- 1
0
votes
1
answer
276
views
Checkpoints ValueError with downloading HuggingFace models
I am having trouble downloading deepseek_vl_v2 into my computer.
Here is the error in my terminal
ValueError: The checkpoint you are trying to load has model type
deepseek_vl_v2 but Transformers does ...
- 13
0
votes
0
answers
46
views
Why am I getting this error and how to solve this?
def initialize_llm(
save_dir: str,
max_new_tokens: int = 500,
temperature: float = 0.1,
repetition_penalty: float = 1.2,
top_p: float = 0.95,
...
0
votes
0
answers
13
views
Problem wth the `generate()` method of `T5ForConditionalGeneration`
I have trained a custom version of the T5 transformer for a text2text task. For this, I had to define two tokenizers , tokenizer_src and tokenizer_tgt as different tokenization strategies were ...
- 666
0
votes
0
answers
29
views
Triggering Space Updates on Dataset Changes on HuggingFace
Hi everyone,
I’ve created a Hugging Face Dataset that I’m utilizing within my Hugging Face Spaces applications. I’m looking for a way to automatically restart or update these Spaces whenever ...
0
votes
1
answer
42
views
HuggingFace Model - OnnxRuntime - Jupyter Notebook Print Model Summary
Thank you very much for reading my question , sorry if it is an obvious question.
I use anaconda navigator : piped install the model whisper from OpenAi, which is an audio to text transformer model, I ...
- 89
0
votes
1
answer
40
views
how to create a Natural Language Inference pipeline in haystack
Could anyone help me with some advice on how to create a Natural Language Inference pipeline in haystack
I want to use the Haystack framework to create a pipeline for Natural Language Inference on the ...
- 2,689
0
votes
0
answers
18
views
Jupyter Notebook Kernel dies after trying to load libraries
I have Macbook with M2 Chip. I have more than 700Gb free on my laptop.
I want to load some hugging face models to my script.
When ever I do this (this is the only lines of code):
from transformers ...
- 3,895
-1
votes
0
answers
34
views
Integrating hugging face public space api with wix chat
I am using wix chatbot and I need to integrate my public space API in the chat, but I am struck in creating the request payload to my API.
I am not sure how to build a request pay load for the API.
By ...
- 29
-1
votes
0
answers
36
views
I can't train a model from a HuggingFace tutorial for "Translation"
im new in this kind of proyects and i want to try a tutorial for translation from HugginFace (Here is the link :text). I'm using my own custom dataset that contains two columns , one for spanish(...
0
votes
1
answer
35
views
Huggingface Push_to_hub Permission denied for certain names
So I am retraining a whisper model and have it saved in a certain path (model_name_or_path).
When I want to push it to the hub I sometimes get a [Errno 13] Permission denied
I can push the adapter but ...
- 97
0
votes
1
answer
35
views
Fine-tuning a Text2Text LLM using different tokenizers for input and output
I’m just starting to explore the Hugging Face library and have a question related to Text2Text models.
Suppose I have a model1 (a Text2Text model, e.g. BART) pre-trained on a masked language modeling ...
- 666
0
votes
0
answers
22
views
Where are LangChain's chat templates stored?
You know how when you use chains or agents, LangChain automatically adds all the necessary chat templates?
Well, I decided to look for them, to see how they actually look. But, I could not find them ...
- 11
0
votes
0
answers
27
views
Unable to load a newly trained tokenizer from local files
I wanted to add some tokens to a GPTNeoXTokenizerFast tokenizer, but since there is no train function I had to use the train_new_from_iterator method from the inhereted PreTrainedTokenizerFast class....
- 51
0
votes
0
answers
15
views
How to make Hugging Face's .map() method map a dataset chunck per chunck?
I am currently trying to train a Hugging Face model with a local dataset. I am also using Hugging Face's datasets library to load my local data with the Dataset class and the .from_json() method. ...
- 21
0
votes
1
answer
219
views
What's causing the high input token count in Huggingface's smolagents?
I was trying out Huggingface's new framework to build agents, named 'smolagents', and one think struck out to me when i ran the tool_calling_agents and the code_agents as well.
The input token count ...
1
vote
0
answers
308
views
Cannot download Llama 3.2 3B model using Unsloth and Hugging Face
I want to locally fine-tune using my own dataset and then save the Llama 3.2-3B model locally too. I have an Anaconda setup and I'm on the base environment, where I can see clearly that unsloth and ...
- 151
0
votes
0
answers
50
views
RuntimeError: Expected tensor for argument #1 'indices' to have one of the following scalar types: Long, Int; but got MPSFloatType instead
I want to apply Integrated Gradients as XAI method on a pretrained huggingface model. Inputs are movie reviews and I use Captum to generate attributions for each token.
But I don't get my code to run. ...
- 33
0
votes
0
answers
46
views
How can HuggingFaceEndpoint instance not need a quantization config or tokenizer?
My original goal was to make a base chain class so I could further instantiate a chain with a LLM of my choice (e.g. gpt-4o-mini or meta-llama/Meta-Llama-3-8B etc).
I've noticed that ...
0
votes
0
answers
45
views
How can I group PyTorch Profiler events by layer hierarchy when profiling a Hugging Face Transformer?
I'm using PyTorch Profiler to inspect inference performance on a Hugging Face Transformer (e.g., Qwen model). I have code that successfully captures operator-level profiling information (like aten::mm,...
- 1
0
votes
0
answers
43
views
How does batch option work in pipeline transformers library
I have a collection of news articles and I want to produce some new (unbiased) news articles using meta-llama/Meta-Llama-3-8B-Instruct. The articles are in a huggingface Dataset and to feed the ...
1
vote
1
answer
124
views
How to get this C# code working for HuggingFace models
I am doing some research and I have to use LLM models on different platforms APIs
1- OpenAI ChatGPT 4
2- Groq Llama 3.2
3- HuggingFace Llama 3.3
I built code that works on OpenAI ChatGPT 4 & ...
- 8,044
1
vote
1
answer
353
views
Could not create share link. Missing file: …\gradio\frpc_windows_amd64_v0.3
I'm trying to use MS's OmniParser now. When I run gradio_demo.py, the following error occurs.
(omni) C:\Users\ingeun\OmniParser>python gradio_demo.py --icon_detect_model weights/icon_detect_v1_5/...
- 11
0
votes
0
answers
52
views
Calling huggingface APIs fails
This is my first time to use huggingface.
I want to call its API to answer a prompt.
Here is what I have so far:
import requests
# Define API details
API_URL = "https://api-inference.huggingface....
- 8,044
1
vote
0
answers
21
views
tokenizer.train_from_iterator throwing TypeError: expected string or buffer
I'm trying to build a custom Tokenizer for a project, and I'm getting error for tokenizer.train_from_iterator:
class IngenxPreTokenizer:
def pre_tokenize(self, pretok: PreTokenizedString):
...
0
votes
0
answers
58
views
Unauthorized access Transformer.js even when i am authenticated using huggingface-cli
I was trying to experiment with transformers.js with microsoft phi-3
import { pipeline } from "@xenova/transformers";
const generator = await pipeline(
"text-generation",
&...
- 328
0
votes
0
answers
90
views
BLEURT evaluation metric consumed too much RAM
The BLEURT codes almost used up all the 24GB RAM of NVIDIA GeForce RTX 4090 to evaluate just 1 set of sentences.
ref = 'reference sentence here'
hypo = 'hypothesis sentence here'
scores = {}
import ...
- 54.3k
0
votes
0
answers
39
views
HuggingFace Trainer receive IterableDataset as the input, how to resume from checkpoint and How epoch iter when this kind of dataset occures
Firstly, the trainig args is set by code downbelow. Cause receive IterableDataset,and I pass max_steps as the control button, so the setting goes this way below.
elif args.max_steps > 0: # Rely on ...
- 3