Asankhaya Sharma's picture

Asankhaya Sharma

codelion

·

http://asankhaya.github.io/

AI & ML interests

AI/ML, Dev Tools and Application Security

Recent Activity

liked a model 8 days ago

codelion/MathCoT

updated a model 8 days ago

codelion/MathCoT

updated a model 8 days ago

codelion/MathCoT

View all activity

Organizations

codelion's activity

upvoted a paper 9 days ago

Chain of Code: Reasoning with a Language Model-Augmented Code Emulator

Paper • 2312.04474 • Published Dec 7, 2023 • 30

upvoted 2 collections about 1 month ago

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 9 items • Updated 7 days ago • 97

indic-evals

Translated versions of popular LLM benchmarks. • 4 items • Updated Oct 23 • 2

upvoted 5 papers 2 months ago

Writing in the Margins: Better Inference Pattern for Long Context Retrieval

Paper • 2408.14906 • Published Aug 27 • 138

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation

Paper • 2409.12941 • Published Sep 19 • 22

Chain-of-Thought Reasoning Without Prompting

Paper • 2402.10200 • Published Feb 15 • 101

Re-Reading Improves Reasoning in Language Models

Paper • 2309.06275 • Published Sep 12, 2023 • 3

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published Sep 19 • 135

upvoted 2 articles 3 months ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Sep 18

• 205

Article

Faster fine-tuning using TRL & Unsloth

Jan 10

• 41

upvoted 3 papers 3 months ago

Patched RTC: evaluating LLMs for diverse software development tasks

Paper • 2407.16557 • Published Jul 23 • 1

Evaluating Pre-trained Language Models for Repairing API Misuses

Paper • 2310.16390 • Published Oct 25, 2023 • 1

Patched MOA: optimizing inference for diverse software development tasks

Paper • 2407.18521 • Published Jul 26 • 1

upvoted 2 articles 5 months ago

Article

TGI Multi-LoRA: Deploy Once, Serve 30 Models

Jul 18

• 52

Article

Announcing BigCodeBench-Hard, and More

By

•

Jul 24

• 10

upvoted a collection 5 months ago

LLaVA-Next-Interleave

7 items • Updated Oct 4 • 16

upvoted a collection 7 months ago

Securade.ai

All models, datasets and tools related to https://securade.ai • 2 items • Updated May 25 • 1

upvoted a paper 8 months ago

FlowMind: Automatic Workflow Generation with LLMs

Paper • 2404.13050 • Published Mar 17 • 33

upvoted 2 papers about 1 year ago

Large Language Model for Science: A Study on P vs. NP

Paper • 2309.05689 • Published Sep 11, 2023 • 20

CodePlan: Repository-level Coding using LLMs and Planning

Paper • 2309.12499 • Published Sep 21, 2023 • 73