Aritra Roy Gosthipaty's picture

Aritra Roy Gosthipaty PRO

ariG23498

·

https://arig23498.github.io/

AI & ML interests

Deep Representation Learning

Recent Activity

published an article about 11 hours ago

🚀 Deploying OLMo-7B with Text Generation Inference (TGI) on Hugging Face Spaces

commented on their article about 12 hours ago

🚀 Build a Qwen 2.5 VL API endpoint with Hugging Face spaces and Docker!

updated a model 4 days ago

ariG23498/layerskip-hf-smollm-135m-topv2

View all activity

Articles

🚀 Deploying OLMo-7B with Text Generation Inference (TGI) on Hugging Face Spaces

about 11 hours ago

🚀 Build a Qwen 2.5 VL API endpoint with Hugging Face spaces and Docker!

Simplifying Alignment: From RLHF to Direct Preference Optimization (DPO)

Timm ❤️ Transformers: Use any timm model with transformers

Controlling Language Model Generation with NVIDIA's LogitsProcessorZoo

Welcome PaliGemma 2 – New vision language models by Google

Faster Text Generation with Self-Speculative Decoding

Hugging Face Welcomes the Qwen2.5-Coder Series

PyTorchModelHubMixin: Bridging the Gap for Custom AI Models on Hugging Face

Hugging Face welcomes the Aya Expanse family of multilingual models

🧨 Diffusers welcomes Stable Diffusion 3.5 Large

Llama can now see and run on your device - welcome Llama 3.2

Understanding Vector Quantization in VQ-VAE

Building DoRA Support for Embedding Layers in PEFT

How to communicate in a Pull Request?

The Workflow of PEFT

Announcing New Hugging Face and KerasHub integration

Conditional Probability

What is Probability?

Counting 'n' objects

Organizations

ariG23498's activity

published an article about 11 hours ago

Article

🚀 Deploying OLMo-7B with Text Generation Inference (TGI) on Hugging Face Spaces

By

•

about 11 hours ago

commented on 🚀 Build a Qwen 2.5 VL API endpoint with Hugging Face spaces and Docker! about 12 hours ago

Hi @lseanlon ! Thank you for your interest in this work. The premise of this blog post was to show users how to build a POC quickly (as you have mentioned), and not show production usage.

Note: It might be interesting for you to showcase some tricks to speedup the inference time. I will be very willing to see what you come up with and also add it to this article giving you due credits of course. 🤗

updated a model 4 days ago

ariG23498/layerskip-hf-smollm-135m-topv2

Updated 4 days ago • 13

updated a Space 4 days ago

Running on Zero

Flux Edit

Using Flux Edit

New activity in ariG23498/flux-edit 4 days ago

update seeding

#7 opened 4 days ago by

add numpy import

#6 opened 4 days ago by

Update requirements.txt

#5 opened 4 days ago by

Update app.py to acknowledge ByteDance

#2 opened 4 days ago by

smol fix

#4 opened 4 days ago by

add randomized seed option

#3 opened 4 days ago by

upvoted an article 4 days ago

Article

Mixture of Experts Explained

Dec 11, 2023

• 283

updated a collection 4 days ago

Model Deployment with Spaces

Deploy models to Spaces and Consume them through an API • 4 items • Updated about 12 hours ago • 1

updated a Space 4 days ago

Tgi Docker Olmo

TGI deployment of OLMo2

published a Space 4 days ago

Tgi Docker Olmo

TGI deployment of OLMo2

updated a Space 4 days ago

GPT2 API

updated a collection 4 days ago

Model Deployment with Spaces

Deploy models to Spaces and Consume them through an API • 4 items • Updated about 12 hours ago • 1

upvoted an article 4 days ago

Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

By

•

4 days ago

• 22

upvoted a collection 4 days ago

DeepSeek R1 (All Versions)

DeepSeek R1 - the most powerful reasoning open-source model - available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 29 items • Updated about 3 hours ago • 136