Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
SelmaNajih001 
posted an update 27 days ago
Post
2270
Finally, I uploaded the model I developed for my master’s thesis! Given a financial event, it provides explained predictions based on a dataset of past news and central bank speeches.
Try it out here:
SelmaNajih001/StockPredictionExplanation
(Just restart the space and wait a minute)

The dataset used for RAG can be found here:
SelmaNajih001/FinancialNewsAndCentralBanksSpeeches-Summary-Rag
While the dataset used for the training is:
SelmaNajih001/FinancialClassification

I also wrote an article to explain how I've done the training. You can find it here https://huggingface.co/blog/SelmaNajih001/explainable-financial-predictions

flexyco

can help me to understand context window
like when i say" what is ai " and ai give me response and he aslo send context soo send time ai take context to understand what user say before
like output is 1k token + 500 token is context window as a summary ??

·
SelmaNajih001

The context window is the total number of tokens a model can process at once, including both your input (question + previous context) and the model’s output (its answer).
So if the model gives a 1,000 token answer using 500 tokens of prior context, it’s using 1,500 tokens of its context window in total.
Just a reminder, the model I've uploaded answer just to events. As it was trained with GRPO to answer a specific question.
Hope I've answered your question!

In this post