I'm working on a multiprocessing python application where multiple processes need access to a large, pre-loaded spaCy NLP model (e.g., en_core_web_lg). Since the model is memory-intensive, I want to avoid loading it separately in each process, since I quickly run…
I'm trying to build my Docker image, but it's taking forever. Even when I leave it to continue building, it fails after a long time. Here is my Dockerfile: FROM ubuntu:24.04 # Install Python and pip RUN apt-get update &&…
I'm doing a NLP project on vscode " amazon reviews sentiment analyzer" every thing is going ok until I reached the part for importing transformers when I'm installing transformers from pip Im getting this error : error: subprocess-exited-with-error × Preparing…
Background I have created an application that queries the user for facts, then allows them to set parts of these facts as fill in the blanks. One of the key ideas is the user will be able to create multiple…
this is my current code: from langchain.llms import HuggingFacePipeline from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, BitsAndBytesConfig from langchain import PromptTemplate, LLMChain import torch model_id = "../models/openbuddy-llama2-34b-v11.1-bf16" tokenizer = AutoTokenizer.from_pretrained(model_id) nf4_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_quant_type='nf4', bnb_4bit_use_double_quant=False, max_memory=24000 ) model =…
I have a dataset of twitter texts. Most of the tweets in this dataset are in Persian and some of them are in Arabic. I want to find Arabic tweets. Is there an API or a tool that can do…
I have created a API script with FastAPI to run a HF transformers' NER model. However I am puzzled to see that the output returning from the API doesn't match the output I get if run the model directly (the…
I had registered for Free level Twitter API recently and I would like to use Tweepy to help me in extracting tweets from user. api_key = config['twitter']['api_key'] api_secret = config['twitter']['api_key_secret'] access_token = config['twitter']['access_token'] access_token_secret = config['twitter']['access_token_secret'] auth = tweepy.OAuthHandler(api_key, api_secret)…
I am having the data as docx files and I want to use them to fine-tune the Falcon model. From what I see the data used to train the model was in json format. How can I convert my data…
I have a piece of text of 4226 characters (316 words + special characters) I am trying different combinations of min_length and max_length to get summary print(summarizer(INPUT, max_length = 1000, min_length=500, do_sample=False)) With the code: The code is summarizer =…