6 21 81

dev7halo

HaloKim

AI & ML interests

None yet

Recent Activity

liked a model 2 days ago

cccczshao/CALM-L

liked a dataset 16 days ago

LGAI-EXAONE/Ko-LongRAG

reacted to gokaygokay's post with 🔥 16 days ago

FlashPack: Lightning-Fast Model Loading for PyTorch https://github.com/fal-ai/flashpack FlashPack — a new, high-throughput file format and loading mechanism for PyTorch that makes model checkpoint I/O blazingly fast, even on systems without access to GPU Direct Storage (GDS). With FlashPack, loading any model can be 3–6× faster than with the current state-of-the-art methods like accelerate or the standard load_state_dict() and to() flow — all wrapped in a lightweight, pure-Python package that works anywhere.

View all activity

Organizations

upvoted a collection about 2 months ago

Tulu 3 Datasets

Collection

All datasets released with Tulu 3 -- state of the art open post-training recipes. • 33 items • Updated Sep 18 • 95

upvoted an article 2 months ago

Article

Implementing MCP Servers in Python: An AI Shopping Assistant with Gradio

Jul 31

•

upvoted an article 3 months ago

Article

Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training

Aug 8

•

upvoted an article 4 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

Jul 8

•

720

upvoted a paper 5 months ago

Orthogonal Finetuning Made Scalable

Paper • 2506.19847 • Published Jun 24 • 8

upvoted 2 papers 7 months ago

LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs

Paper • 2504.14655 • Published Apr 20 • 20

PaperBench: Evaluating AI's Ability to Replicate AI Research

Paper • 2504.01848 • Published Apr 2 • 36

upvoted 2 articles 8 months ago

Article

LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!

Mar 7

•

Article

Efficient LLM Pretraining: Packed Sequences and Masked Attention

Oct 7, 2024

•

upvoted a paper 8 months ago

NeoBERT: A Next-Generation BERT

Paper • 2502.19587 • Published Feb 26 • 38

upvoted a paper 10 months ago

PaSa: An LLM Agent for Comprehensive Academic Paper Search

Paper • 2501.10120 • Published Jan 17 • 52

upvoted an article about 1 year ago

Article

Selective fine-tuning of Language Models with Spectrum

Sep 3, 2024

•

upvoted 8 articles over 1 year ago

Article

Tokenization Is A Dead Weight (Tokun Part 1)

Jun 27, 2024

•

Article

Docmatix - a huge dataset for Document Visual Question Answering

Jul 18, 2024

•

Article

Mergoo: Efficiently Build Your Own MoE LLM

Jun 3, 2024

•

Article

Rank-Stabilized LoRA: Unlocking the Potential of LoRA Fine-Tuning

Feb 20, 2024

•

Article

Merge Large Language Models with mergekit

Jan 9, 2024

•

145

Article

Train a Llama model from scratch

Jul 29, 2024

•

Article

Fine-tuning LLMs with Singular Value Decomposition

Jun 2, 2024

•

Article

Uncensor any LLM with abliteration

Jun 13, 2024

•

713

dev7halo

AI & ML interests

Recent Activity

Organizations

dev7halo's activity

Implementing MCP Servers in Python: An AI Shopping Assistant with Gradio

Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training

SmolLM3: smol, multilingual, long-context reasoner

LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!

Efficient LLM Pretraining: Packed Sequences and Masked Attention

Selective fine-tuning of Language Models with Spectrum

Tokenization Is A Dead Weight (Tokun Part 1)

Docmatix - a huge dataset for Document Visual Question Answering

Mergoo: Efficiently Build Your Own MoE LLM

Rank-Stabilized LoRA: Unlocking the Potential of LoRA Fine-Tuning

Merge Large Language Models with mergekit

Train a Llama model from scratch

Fine-tuning LLMs with Singular Value Decomposition

Uncensor any LLM with abliteration