Skip to content
View Bansnetsajak007's full-sized avatar
🤘
Hell Yeahhh
🤘
Hell Yeahhh

Highlights

  • Pro

Block or report Bansnetsajak007

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Bansnetsajak007/README.md

Sajak Basnet

Machine Learning and AI engineer in training, focused on data-centric AI, algorithmic fundamentals, and end-to-end system design. I work at the intersection of theory and engineering, with a strong emphasis on core mathematics, learning algorithms, and building real AI systems from the ground up. My current focus includes domain-specific LLMs, dataset curation, tokenization pipelines, training, evaluation, and reproducible experimentation.


Focus

  • AI & ML theory (math-first understanding)
  • Domain-specific LLMs
  • Dataset engineering & tokenization
  • Training, evaluation, and reproducibility

Tech

Python · NumPy · PyTorch · scikit-learn · Flask · FastAPI


Current Work

Training a domain-specific AI/ML LLM from scratch covering data acquisition, curation, tokenization, training, and evaluation.


Connect

Pinned Loading

  1. ai-ml-domain-llm ai-ml-domain-llm Public

    An engineering-focused project covering data acquisition, dataset curation, tokenization, training, and evaluation of an AI/ML-focused LLM.

    Python 4 2

  2. BasNet-Spatial-Attention-DHCR BasNet-Spatial-Attention-DHCR Public

    PyTorch implementation of BasNet, a residual CNN with spatial self-attention for handwritten Devanagari character recognition, focusing on stroke-preserving downsampling and efficient feature learn…

    Jupyter Notebook 4

  3. coreMachineLearningandDeepLearning coreMachineLearningandDeepLearning Public

    Understanding core DeepLearning , Mathematical intuition of Algorithms , Implementing algorithms from Stratch

    Jupyter Notebook 1

  4. gradient_Descent_implementation gradient_Descent_implementation Public

    Simple Linear Regression from Scratch using Gradient Descent to Predict Company Sales (in Python, no ML libraries)

    Jupyter Notebook 2