Ankush Singal's picture

Ankush Singal

Andyrasika

·

https://github.com/andysingal

AI & ML interests

None yet

Articles

Knowledge Distillation for Fine-Tuning a GPT-3.5 Judge: Enhancing Accuracy and Performance

Estimating Memory Consumption of LLMs for Inference and Fine-Tuning for Cohere Command-R+

RAG Empowerment: Cohere C4AI Command-R and Transformers Unveiled

Elevate Responses: RAG with LlamaIndex & MongoDB

Revolutionizing Video Transcription: Unveiling Gemma-2b-it and Langchain in the Era of Transformers

Transformers and Quadrant: Revolutionizing Data Integration for NLP Tasks

Quantization of Transformer Models with Neural Compressor

Unleashing the Power of Unsloth and QLora:Redefining Language Model Fine-Tuning

Unleashing the Power of Logprobs in Language Models: A Practical Guide

Unveiling TinyLlama: An Inspiring Dive into a Revolutionary Small-Scale Language Model

Multimodal IDEFICS: Unveiling the Transparency & Power of Open Visual Language Models

Streamlining Data Management with Hugging Face and DVC: A Seamless Integration

Leveraging Transformers and PyTorch for Multiple Choice Question Tasks

Uniting Forces: Integrating Hugging Face with Langchain for Enhanced Natural Language Processing

Detecting the Deceptive: Unmasking Deep Fake Voices

Hearing is Believing: Revolutionizing AI with Audio Classification via Computer Vision

InfiniText: Empowering Conversations & Content with Mistral-7B-Instruct-v0.1

Samantha and Mistral 7B: A Powerful and Versatile Language Model Duo

Organizations

Andyrasika's activity

upvoted an article 3 days ago

Article

Knowledge Distillation for Fine-Tuning a GPT-3.5 Judge: Enhancing Accuracy and Performance

By

•

3 days ago

• 2

upvoted a paper 6 days ago

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Paper • 2404.07143 • Published Apr 10 • 92

upvoted an article 17 days ago

Article

🦙⚗️ Using Llama3 and distilabel to build fine-tuning datasets

By

•

20 days ago

• 54

upvoted a collection 20 days ago

Llama 3 - Smashed

Many variations of Llama 3 with many compression techniques. • 81 items • Updated 14 days ago • 4

upvoted an article 20 days ago

Article

Estimating Memory Consumption of LLMs for Inference and Fine-Tuning for Cohere Command-R+

By

•

20 days ago

• 4

upvoted 5 articles about 1 month ago

Article

Transformers and Quadrant: Revolutionizing Data Integration for NLP Tasks

By

•

Feb 21

• 1

Article

Revolutionizing Video Transcription: Unveiling Gemma-2b-it and Langchain in the Era of Transformers

By

•

Mar 12

• 2

Article

Elevate Responses: RAG with LlamaIndex & MongoDB

By

•

Mar 28

• 2

Article

DS-MoE: Making MoE Models More Efficient and Less Memory-Intensive

By

•

Apr 9

• 26

Article

RAG Empowerment: Cohere C4AI Command-R and Transformers Unveiled

By

•

Apr 7

• 9

upvoted a paper 2 months ago

Beyond Language Models: Byte Models are Digital World Simulators

Paper • 2402.19155 • Published Feb 29 • 44

upvoted a paper 3 months ago

FiT: Flexible Vision Transformer for Diffusion Model

Paper • 2402.12376 • Published Feb 19 • 46