Akmmus AI

@akmmusai

NLP-focused AI Research Lab, India

Trichy, IndiaJoined August 2023

About

Akmmus AI is a newly established NLP-focused AI research lab from Trichy, India. Our broad areas of research interest are natural language processing and deep learning. Specifically, we are interested in large language models and the relevant topics.

Available for

Nothing here yet.

Akmmus AI's blogs

Akmmus AIblog.akmmusai.pro14 posts

Articles Threads Comments

Recently published

blog.akmmusai.pro

LLAMAFACTORY: Unified Efficient Fine-Tuning of 100+ Language Models

TLDR - LLAMAFACTORY, a unified framework that integrates a suite of cutting-edge efficient LLM fine-tuning methods. It allows users to flexibly customize the fine-tuning of 100+ LLMs without the need for coding through the built-in web UI LLAMABOARD....

Mar 22, 20242 min read

blog.akmmusai.pro

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (Short Summary)

TLDR - Gemini 1.5 Pro is a new LLM in Google's Gemini family known for its advanced capabilities. Gemini 1.5 Pro outperforms models like Claude 2.1 and GPT-4 Turbo by handling up to 10 million tokens of information context (vs. 200k and 128k respecti...

Mar 12, 20242 min read

blog.akmmusai.pro

Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

TLDR - Large Language Models (LLMs) offer new capabilities but evaluating their alignment with human preferences is difficult. Chatbot Arena is a new open platform introduced to specifically address this evaluation challenge. For evaluation, this pla...

Mar 9, 20242 min read

blog.akmmusai.pro

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

TLDR - Training Large Language Models (LLMs) presents significant memory challenges because of their large sizes. Approaches like LoRA typically underperform training with full-rank weights in both pre-training and fine-tuning stages since they limit...

Mar 9, 20242 min read

blog.akmmusai.pro

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (short summary)

TLDR - Large language models (LLMs) are getting larger to achieve better performances, but their large sizes create bottlenecks for deployment. Model compression techniques, like pruning, make LLMs smaller by removing some parameters while maintainin...

Mar 9, 20242 min read

Akmmus AI

About

Available for

Akmmus AI's blogs

Recently published

LLAMAFACTORY: Unified Efficient Fine-Tuning of 100+ Language Models

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (Short Summary)

Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (short summary)

Search Hashnode

Akmmus AI

About

Available for

Akmmus AI's blogs

Recently published

LLAMAFACTORY: Unified Efficient Fine-Tuning of 100+ Language Models

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (Short Summary)

Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (short summary)