Prithiv Sakthi's picture

Prithiv Sakthi

prithivMLmods

·

https://huggingface.co/strangerzonehf

AI & ML interests

computer vision, multimodality, adapters @starngerzonehf @strangerguardhf

Recent Activity

updated a Space about 1 hour ago

prithivMLmods/Agent-Dino

reacted to davanstrien's post with 🧠 about 1 hour ago

Hacked together a way to log trl GRPO training completions to a 🤗 dataset repo. This allows you to: - Track rewards from multiple reward functions - Treat the completion and rewards from training as a "proper" dataset and do EDA - Share results for open science The implementation is super hacky, but I'm curious if people would find this useful. To push completions to the Hub, you just need two extra parameters: ``` log_completions=True log_completions_hub_repo='your-username/repo-name' ``` Example dataset: https://huggingface.co/datasets/davanstrien/test-logs Colab: https://colab.research.google.com/drive/1wzBFPVthRYYTp-mEYlznLg_e_0Za1M3g

updated a model about 3 hours ago

strangerzonehf/Flux-Ultimate-LoRA-Collection

View all activity

Organizations

prithivMLmods's activity

upvoted a collection about 4 hours ago

DeepSeek

11 items • Updated 3 days ago • 3

upvoted a collection about 7 hours ago

The Ultimate Collection of Code Classifiers

🔥 15 classifiers, 124M parameters, one per programming language— for assessing the educational value of GitHub code • 15 items • Updated about 5 hours ago • 9

upvoted a paper about 7 hours ago

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published 1 day ago • 82

upvoted an article 1 day ago

Article

Fixing Open LLM Leaderboard with Math-Verify

7 days ago

• 23

upvoted 2 collections 1 day ago

Deepfake Classification 022025

based on recent dataset • 5 items • Updated about 14 hours ago • 6

Deepfake Quality Assessment

Controllable Classification of Good and Bad Quality Deepfakes • 6 items • Updated 1 day ago • 4

upvoted an article 3 days ago

Article

Fine-tuning SmolLM with Group Relative Policy Optimization (GRPO) by following the Methodologies

By

•

3 days ago

• 15

upvoted a collection 3 days ago

Image Annotation & Captioning

Trained based on Flux-generated images and their enhanced prompt captioning and annotations in a simple JSON format. • 3 items • Updated 3 days ago • 10

upvoted 3 collections 7 days ago

Deepfake Quality Assess Datasets

Classification of Good and Bad Quality Deepfakes { Datasets } • 4 items • Updated 7 days ago • 3

Purposeful Conversational Models 🚅

providing assistance • 7 items • Updated 1 day ago • 10

Coder Models Equilibrium 🧑🏻‍💻

Coder Models • 2 items • Updated 7 days ago • 8

upvoted a collection 9 days ago

Reasoning is all you need 🌠

The garage for 14B and 7B reasoning models, listed based on benchmarks. • 24 items • Updated 9 days ago • 9

upvoted 2 articles 10 days ago

Article

Open R1: Update #2

By

and 6 others •

10 days ago

• 179

Article

Fine-tune Deepseek-R1 with a Synthetic Reasoning Dataset

By

•

10 days ago

• 35

upvoted 2 collections 10 days ago

Vision Infer Custom

VLM - Multimodality • 2 items • Updated 26 days ago • 7

Reasoning Exp Domain Models 🧠

Based on Qwen's 2 vL • 2 items • Updated 10 days ago • 7

upvoted a paper 13 days ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published 16 days ago • 187

upvoted a paper 14 days ago

LIMO: Less is More for Reasoning

Paper • 2502.03387 • Published 15 days ago • 56

upvoted 2 articles 15 days ago

Article

Agentic RAG Stack (2/5) - Augment retrieval results by reranking using Sentence Transformers

By

•

15 days ago

• 9

Article

Agentic RAG Stack (1/5) - Index and retrieve documents for vector search using Sentence Transformers and DuckDB

By

•

24 days ago

• 18