sanowl

Follow

👽

San sanowl

👽

Follow

working on mechanistic interpretability

89 followers · 102 following

Cyrion Labs
AUIS
https://sanowl.github.io/

Achievements

Achievements

Highlights

Pro

sanowl/README.md

San

ML engineer and mechanistic interpretability researcher working on agents.

Most Used Languages

Contact

Email: san.hashimhama@outlook.com

Pinned Loading

LSLM-Listening-while-Speaking-Language-Model LSLM-Listening-while-Speaking-Language-Model Public

LSLM implements full duplex modeling in interactive speech language models, based on research by Ma et al. (2024). This project advances human-computer interaction through real-time spoken dialogue…

Python 85 9
Self-Correcting-LLM--Reinforcement-Learning- Self-Correcting-LLM--Reinforcement-Learning- Public

This my attempt to create Self-Correcting-LLM based on the paper Training Language Models to Self-Correct via Reinforcement Learning by google

Python 38 8
OmegaPRM OmegaPRM Public

this is an implementation for the paper Improve Mathematical Reasoning in Language Models by Automated Process Supervision from google deepmind

Python 44 4
CoRAG CoRAG Public

this is based on the paper Chain-of-Retrieval Augmented Generation

Python 14 1
Drag-and-Drop-LLMs-Zero-Shot-Prompt-to-Weights Drag-and-Drop-LLMs-Zero-Shot-Prompt-to-Weights Public

Python 31 5
Efficient-LLM-Scheduling-by-Learning-to-Rank Efficient-LLM-Scheduling-by-Learning-to-Rank Public

This project implements an efficient scheduling system for Large Language Model (LLM) inference, as described in the paper "Efficient LLM Scheduling by Learning to Rank"

Python 9