# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="ibrahimlasfar/elasfar-AI")# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("ibrahimlasfar/elasfar-AI")
model = AutoModelForCausalLM.from_pretrained("ibrahimlasfar/elasfar-AI")Quick Links
elasfar-AI
Model Description
The elasfar-AI model is a fine-tuned language model designed to answer questions about
my personal portfolio, including my projects (e.g., Mark AI ), skills, and professional experience.
It is intended for use in an interactive Q&A feature on my personal website for educational and
experimental purposes.
Intended Use
- Primary Use Case: Powering a Q&A feature to provide information about my skills, projects, and experience.
- Intended Audience: Visitors to my personal portfolio website, including potential employers, collaborators, or curious users.
- Tasks: Question answering, text generation.
Training Data
The model was fine-tuned on a custom dataset (training_data.csv) containing question-answer pairs related to
my personal portfolio, projects, and skills. The dataset includes curated examples to ensure accurate and relevant responses.
How to Use
You can use this model via the Hugging Face Inference API. Example:
from huggingface_hub import InferenceClient
client = InferenceClient(token="YOUR_HF_TOKEN")
response = client.text_generation("How the United States was discovered ?", model="ibrahimlasfar/elasfar-AI")
print(response)
- Downloads last month
- -
# Gated model: Login with a HF token with gated access permission hf auth login