t1u1's picture

t1u1

t1u1

·

AI & ML interests

None yet

Recent Activity

reacted to mitkox's post with 👍 about 3 hours ago

llama.cpp is 26.8% faster than ollama. I have upgraded both, and using the same settings, I am running the same DeepSeek R1 Distill 1.5B on the same hardware. It's an Apples to Apples comparison. Total duration: llama.cpp 6.85 sec <- 26.8% faster ollama 8.69 sec Breakdown by phase: Model loading llama.cpp 241 ms <- 2x faster ollama 553 ms Prompt processing llama.cpp 416.04 tokens/s with an eval time 45.67 ms <- 10x faster ollama 42.17 tokens/s with an eval time of 498 ms Token generation llama.cpp 137.79 tokens/s with an eval time 6.62 sec <- 13% faster ollama 122.07 tokens/s with an eval time 7.64 sec llama.cpp is LLM inference in C/C++; ollama adds abstraction layers and marketing. Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.

reacted to lewtun's post with 🚀 about 3 hours ago

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open! 🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1. 🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code. 🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training. Follow along: https://github.com/huggingface/open-r1

liked a model about 6 hours ago

mkurman/Qwen2.5-14B-DeepSeek-R1-1M

View all activity

Organizations

None yet

t1u1's activity

upvoted an article 3 days ago

Article

FuseO1-Preview: System-II Reasoning Fusion of LLMs

By

•

7 days ago

• 9

upvoted a paper 4 days ago

Autonomy-of-Experts Models

Paper • 2501.13074 • Published 5 days ago • 36

upvoted a paper 17 days ago

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Paper • 2501.04519 • Published 19 days ago • 249

upvoted 2 papers 6 months ago

ControlNeXt: Powerful and Efficient Control for Image and Video Generation

Paper • 2408.06070 • Published Aug 12, 2024 • 53

Transformer Explainer: Interactive Learning of Text-Generative Models

Paper • 2408.04619 • Published Aug 8, 2024 • 156

upvoted 2 papers 8 months ago

What If We Recaption Billions of Web Images with LLaMA-3?

Paper • 2406.08478 • Published Jun 12, 2024 • 40

FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation

Paper • 2406.08392 • Published Jun 12, 2024 • 19

upvoted a collection 9 months ago

Meta Llama 3

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated Dec 6, 2024 • 706

upvoted a paper 10 months ago

FeatUp: A Model-Agnostic Framework for Features at Any Resolution

Paper • 2403.10516 • Published Mar 15, 2024 • 16

upvoted 8 papers 11 months ago

Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Paper • 2401.10774 • Published Jan 19, 2024 • 54

Recurrent Drafter for Fast Speculative Decoding in Large Language Models

Paper • 2403.09919 • Published Mar 14, 2024 • 21

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

Paper • 2403.09629 • Published Mar 14, 2024 • 76

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Paper • 2403.03507 • Published Mar 6, 2024 • 184

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Paper • 2403.03853 • Published Mar 6, 2024 • 62

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 608

EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Paper • 2402.17485 • Published Feb 27, 2024 • 191

ChatMusician: Understanding and Generating Music Intrinsically with LLM

Paper • 2402.16153 • Published Feb 25, 2024 • 58