Florian Zimmermeister's picture

Florian Zimmermeister PRO

flozi00

·

AI & ML interests

ASR, German LLM

Recent Activity

liked a Space about 13 hours ago

OuteAI/OuteTTS-0.3-1B-Demo

reacted to MoritzLaurer's post with 👀 1 day ago

Microsoft's rStar-Math paper claims that 🤏 ~7B models can match the math skills of o1 using clever train- and test-time techniques. You can now download their prompt templates from Hugging Face ! 📏 The paper introduces rStar-Math, which claims to rival OpenAI o1's math reasoning capabilities by integrating Monte Carlo Tree Search (MCTS) with step-by-step verified reasoning trajectories. 🤖 A Process Preference Model (PPM) enables fine-grained evaluation of intermediate steps, improving training data quality. 🧪 The system underwent four rounds of self-evolution, progressively refining both the policy and reward models to tackle Olympiad-level math problems—without GPT-4-based data distillation. 💾 While we wait for the release of code and datasets, you can already download the prompts they used from the HF Hub! Details and links here 👇 Prompt-templates docs: https://moritzlaurer.github.io/prompt_templates/ Templates on the hub: https://huggingface.co/datasets/MoritzLaurer/rstar-math-prompts Prompt-templates collection: https://huggingface.co/collections/MoritzLaurer/prompt-templates-6776aa0b0b8a923957920bb4 Paper: https://arxiv.org/pdf/2501.04519

upvoted an article 1 day ago

The Large Language Model Course

View all activity

Organizations

$A\\Ware's profile picture$

flozi00's activity

upvoted an article 1 day ago

Article

The Large Language Model Course

By

•

2 days ago

• 46

upvoted a paper 10 days ago

Scaling Laws for Floating Point Quantization Training

Paper • 2501.02423 • Published 13 days ago • 25

upvoted a paper about 1 month ago

Transformers Can Navigate Mazes With Multi-Step Prediction

Paper • 2412.05117 • Published Dec 6, 2024 • 5

upvoted an article about 1 month ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13, 2024

• 394

upvoted 2 articles 2 months ago

Article

Releasing the largest multilingual open pretraining dataset

By

•

Nov 13, 2024

• 98

Article

SauerkrautLM's Multi-Phase Spectrum Training: A Technical Deep Dive

By

•

Nov 9, 2024

• 9

upvoted a paper 2 months ago

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

Paper • 2411.02355 • Published Nov 4, 2024 • 47

upvoted an article 3 months ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Sep 18, 2024

• 216

upvoted a paper 3 months ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7, 2024 • 169

upvoted an article 3 months ago

Article

Welcome, Gradio 5

Oct 9, 2024

• 100

upvoted 2 papers 4 months ago

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

Paper • 2407.10960 • Published Jul 15, 2024 • 12

Spectrum: Targeted Training on Signal to Noise Ratio

Paper • 2406.06623 • Published Jun 7, 2024 • 12

upvoted a collection 4 months ago

Strong German fp8 LLM's

Strong Large Language Models for the german language in fp8 format • 6 items • Updated Sep 24, 2024 • 3

upvoted 3 papers 4 months ago

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform

Paper • 2405.03003 • Published May 5, 2024 • 7

Qwen2.5-Coder Technical Report

Paper • 2409.12186 • Published Sep 18, 2024 • 140

Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients

Paper • 2407.08296 • Published Jul 11, 2024 • 31

upvoted a collection 4 months ago

INT4 LLMs for vLLM

Accurate INT4 quantized models by Neural Magic, ready for use with vLLM! • 18 items • Updated Sep 26, 2024 • 8

upvoted a collection 5 months ago

FP8 LLMs for vLLM

Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated Oct 17, 2024 • 62

upvoted a collection 6 months ago

Research projects on top of vLLM

Papers cited in https://blog.vllm.ai/2024/07/25/lfai-perf.html • 6 items • Updated Jul 29, 2024 • 12

upvoted an article 6 months ago

Article

The Rise of Agentic Data Generation

By

•

Jul 15, 2024

• 81