Hugging Face's logo
Mayank Mishra's picture
70 45 8

Mayank Mishra

mayank-mishra
DomMaz's profile picture anupamamurthi's profile picture arnaik's profile picture
·
https://mayank31398.github.io/

AI & ML interests

Large Language Models, Distributed Training and Inference

Recent Activity

authored a paper about 19 hours ago
FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference
authored a paper about 19 hours ago
PaTH Attention: Position Encoding via Accumulating Householder Transformations
authored a paper 3 months ago
Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence
View all activity

Organizations

IBM's profile picture BigCode's profile picture Aurora-M/MDEL's profile picture Blog-explorers's profile picture Aurora-M's profile picture IBM Granite's profile picture IBM Research's profile picture

mayank-mishra's activity

New activity in ibm-granite/granite-3.1-2b-instruct 5 months ago

RE-ADD float32 please.

3
#3 opened 5 months ago by
ctranslate2-4you
New activity in ibm-granite/granite-3.1-8b-instruct 6 months ago

Exceptional creative writer

❤️ 🔥 15
5
#1 opened 6 months ago by
SubtleOne
New activity in ibm-granite/granite-3.0-2b-instruct 8 months ago

add base model metadata

🔥 1
#3 opened 8 months ago by
davanstrien
New activity in ibm-granite/granite-3.0-8b-instruct 8 months ago

add base model metadata
#5 opened 8 months ago by
davanstrien
New activity in ibm-granite/granite-3.0-1b-a400m-instruct 8 months ago

Add base model metadata
#2 opened 8 months ago by
davanstrien
New activity in ibm-research/PowerMoE-3b 9 months ago

torch and llama.cpp integration

3
#1 opened 9 months ago by
TobDeBer
New activity in cfahlgren1/model-release-heatmap 10 months ago

Add IBM

3
#5 opened 10 months ago by
mayank-mishra
New activity in ibm-granite/granite-8b-code-instruct-128k 10 months ago

Fix: link to 128k paper

1
#1 opened 10 months ago by
timrbula
New activity in meta-llama/Llama-3.1-405B 11 months ago

405B or 410B ?

2
#8 opened 11 months ago by
alielfilali01
New activity in ibm-granite/granite-3b-code-instruct-2k 11 months ago

Onnx Model Produces Different Output

2
#2 opened about 1 year ago by
runski
New activity in ibm-granite/granite-8b-code-instruct-4k 12 months ago

[AUTOMATED] Model Memory Requirements
#4 opened about 1 year ago by
model-sizer-bot

Function calling and Streaming support

2
#5 opened about 1 year ago by
skumarai
New activity in mayank-mishra/glaive-code-assisstant-v3-20k 12 months ago

[bot] Conversion to Parquet
#1 opened about 1 year ago by
parquet-converter
New activity in ibm-granite/granite-8b-code-instruct-4k 12 months ago

Input context length

3
#6 opened 12 months ago by
dyoung
New activity in ibm-granite/granite-8b-code-instruct-4k about 1 year ago

Official quants?

3
#2 opened about 1 year ago by
joshuaturner
New activity in ibm-granite/granite-20b-code-instruct-8k about 1 year ago

Is it fine to do granite-20b model's inference with bfloat16 dtype?

3
#1 opened about 1 year ago by
lkm1
New activity in ibm-granite/granite-3b-code-instruct-2k-GGUF about 1 year ago

Issue to run the model on Ollama.

3
#1 opened about 1 year ago by
vperrinfr
New activity in ibm-granite/granite-3b-code-base-2k about 1 year ago

Release GGUF models?

3
#5 opened about 1 year ago by
CosmicSound
commented a paper about 1 year ago
New activity in ibm-granite/granite-20b-code-base-8k-GGUF about 1 year ago

3b, 8b, and 34b versions of GGUF?

1
#1 opened about 1 year ago by
tombenninger