8000 shaafsalman (Shaaf Salman) · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View shaafsalman's full-sized avatar

Block or report shaafsalman

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, 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
shaafsalman/README.md

Visitor Badge

Typing SVG


Current Laboratory Point of View

  • Training Open-Source Models using sCoRE and COTS
    Building and training open-source models to simulate efficient, human-like reasoning processes.
  • Synthetic Dataset Generation
    Designing pipelines in langChain to generate structured datasets to enhance machine learning model training on coding problems.
  • Autonomous Repository Solving Agent through SWE Bench
    Developing AI-based agents for solving bugs in repository autonomously.

Writings

Some Maths

GitHub Stats Top Languages

Arsenal

Tech Stack

Popular repositories Loading

  1. Weed-Detector Weed-Detector Public

    Python Program using TensorFlow and karas to differenciate between crop and weed

    Jupyter Notebook 2

  2. PharmaFast PharmaFast Public

    Open-Source Point of Sale System Developed a comprehensive Java Swing-based POS solution with SQL database integration for efficient transaction processing and administrative management. Designed a…

    Java 1

  3. simple-evals-ss simple-evals-ss Public

    Forked from openai/simple-evals

    Python 1

  4. shaafsalman shaafsalman Public

  5. Lumus-Lights Lumus-Lights Public

    JavaScript

  6. experiments experiments Public

    Forked from SWE-bench/experiments

    Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.

    Shell

0