Mayank Mishra's picture

Mayank Mishra

mayank-mishra

·

https://mayank31398.github.io/

AI & ML interests

Large Language Models, Distributed Training and Inference

Recent Activity

new activity 29 days ago

ibm-granite/granite-3.1-2b-instruct:RE-ADD float32 please.

upvoted a collection about 2 months ago

Granite 3.1 Language Models

new activity about 2 months ago

ibm-granite/granite-3.1-8b-instruct:Exceptional creative writer

View all activity

Organizations

mayank-mishra's activity

New activity in ibm-granite/granite-3.1-2b-instruct 29 days ago

RE-ADD float32 please.

#3 opened about 1 month ago by

ctranslate2-4you

upvoted a collection about 2 months ago

Granite 3.1 Language Models

A series of language models with 128K context length trained by IBM licensed under Apache 2.0 license. • 8 items • Updated Dec 18, 2024 • 52

New activity in ibm-granite/granite-3.1-8b-instruct about 2 months ago

Exceptional creative writer

#1 opened about 2 months ago by

authored a paper about 2 months ago

Selective Self-Rehearsal: A Fine-Tuning Approach to Improve Generalization in Large Language Models

Paper • 2409.04787 • Published Sep 7, 2024 • 1

upvoted a paper 3 months ago

SelfCodeAlign: Self-Alignment for Code Generation

Paper • 2410.24198 • Published Oct 31, 2024 • 23

upvoted a collection 3 months ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated about 5 hours ago • 214

New activity in ibm-granite/granite-3.0-2b-instruct 4 months ago

add base model metadata

#3 opened 4 months ago by

New activity in ibm-granite/granite-3.0-8b-instruct 4 months ago

add base model metadata

#5 opened 4 months ago by

New activity in ibm-granite/granite-3.0-1b-a400m-instruct 4 months ago

Add base model metadata

#2 opened 4 months ago by

upvoted a collection 4 months ago

Granite 3.0 Language Models

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated Dec 18, 2024 • 95

updated 2 collections 4 months ago

Power-LM

Dense & MoE LLMs trained with power learning rate scheduler. • 4 items • Updated Oct 17, 2024 • 15

Granite 3.0 Language Models

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated Dec 18, 2024 • 95

New activity in ibm-research/PowerMoE-3b 5 months ago

torch and llama.cpp integration

#1 opened 5 months ago by

updated a collection 5 months ago

Granite Code Models

A series of code models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 23 items • Updated Dec 18, 2024 • 182

upvoted a paper 5 months ago

The Mamba in the Llama: Distilling and Accelerating Hybrid Models

Paper • 2408.15237 • Published Aug 27, 2024 • 39

authored a paper 5 months ago

Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler

Paper • 2408.13359 • Published Aug 23, 2024 • 24

updated a collection 5 months ago

Power-LM

Dense & MoE LLMs trained with power learning rate scheduler. • 4 items • Updated Oct 17, 2024 • 15