Skip to content
View colesmcintosh's full-sized avatar
20 followers · 58 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: QuickdrawAchievement: YOLO

Block or report colesmcintosh

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
colesmcintosh/README.md

What am I doing?

Trying to do the best research I can in LLM's, reasoning, and multi-agent systems. Contributor to LiteLLM and creator of the official LangChain Salesforce Integration.

Currently doing research about advancing LLM reasoning capabilities through entropy injection research, developing production-grade multi-agent architectures, and optimizing large language model performance at scale.

Pinned Loading

  1. chain-of-thought-reranking chain-of-thought-reranking Public

    an approach to optimizing large language model (LLM) responses by extracting, reranking, and refining their internal chain-of-thought (CoT). By focusing on the most coherent and relevant parts of t…

    Jupyter Notebook 3

  2. entropy-injection-cot entropy-injection-cot Public

    An approach to improve language model reasoning by dynamically injecting Chain of Thought (CoT) prompts based on entropy measurements

    Jupyter Notebook 2

  3. langchain-salesforce langchain-salesforce Public

    Langchain integration for Salesforce CRM, providing tools for SOQL queries, object schema inspection, and CRUD operations through Langchain's framework

    Python 2

  4. llama-kernel llama-kernel Public

    Memory-efficient PyTorch kernel for Llama 3.2 inference with 4-bit quantization and advanced optimization techniques

    Python 1

  5. vector-vault vector-vault Public

    A high-performance vector similarity search engine with LSH (Locality-Sensitive Hashing) optimization, written in Go.

    Go

  6. pycuda-numpy-vector-ops pycuda-numpy-vector-ops Public

    Accelerating NumPy Vector Operations with PyCUDA

    Jupyter Notebook