Nyaribari Reuben's picture

15

Nyaribari Reuben

foscraft

·

AI & ML interests

LLMs, VLMs , Vision

Recent Activity

liked a model 26 days ago

mistralai/Mistral-7B-Instruct-v0.3

liked a model 26 days ago

mistralai/Mistral-7B-v0.1

reacted to DavidGF's post with 🔥 6 months ago

🎉 Celebrating One Year of #SauerkrautLM with Two Groundbreaking Releases! We're thrilled to announce the release of SauerkrautLM-v2-14b in two specialized versions: https://huggingface.co/VAGOsolutions/SauerkrautLM-v2-14b-SFT and https://huggingface.co/VAGOsolutions/SauerkrautLM-v2-14b-DPO. Built on the robust Qwen2.5-14B foundation, these models represent a significant leap forward in multilingual AI capabilities. 🔬 Technical Breakthroughs: 💠 Innovative three-phase Fine-Tuning approach 💠 Two-step Spectrum SFT + one-step Spectrum DPO optimization phase for enhanced performance 💠 Balance of German and English language capabilities 💠 Advanced function calling - almost on par with Claude-3.5-Sonnet-20240620 🇩🇪 German Language Excellence: What sets this release apart is our unique achievement in simultaneously improving both German and English capabilities. Through our specialized training approach with over 1.2B tokens across two phases, we've managed to: 💠 Enhance German language understanding and generation (SFT Version > DPO Version) 💠 Maintain authentic German linguistic nuances 💠 Improve cross-lingual capabilities 💠 Preserve cultural context awareness 📊 Training Innovation: Our three-phase approach targeted specific layer percentages (15%, 20% and 25%) with carefully curated datasets, including: 💠 Mathematics-focused content (proprietary classifier-selected) 💠 High-quality German training data 💠 Specialized function calling datasets 💠 Premium multilingual content 🎁 Community Contribution: We're also releasing two new datasets in a few days: 1️⃣ SauerkrautLM-Fermented-GER-DPO: 3,300 high-quality German training samples 2️⃣ SauerkrautLM-Fermented-Irrelevance-GER-DPO: 2,000 specialized samples for optimized function call irrelevance handling Thank you to our incredible community and partners who have supported us throughout this journey. Here's to another year of AI innovation! 🚀

View all activity

Organizations

foscraft's activity

liked 2 models 26 days ago

mistralai/Mistral-7B-Instruct-v0.3

Text Generation • Updated Aug 21, 2024 • 698k • • 1.65k

mistralai/Mistral-7B-v0.1

Text Generation • Updated Jul 24, 2024 • 805k • 3.76k

liked 4 models 8 months ago

openai-community/gpt2

Text Generation • Updated Feb 19, 2024 • 12.7M • • 2.7k

tiiuae/falcon-rw-1b

Text Generation • Updated Jul 12, 2023 • 69.8k • 107

TheBloke/wizard-vicuna-13B-GGML

Updated Jun 9, 2023 • 143

TheBloke/orca_mini_3B-GGML

Updated Jun 25, 2023 • 60

liked 2 models 9 months ago

TheBloke/Llama-2-7B-Chat-GGUF

Text Generation • Updated Oct 14, 2023 • 85.9k • 469

AdamCodd/donut-receipts-extract

Image-to-Text • Updated Jan 11 • 72 • 34

liked a Space 9 months ago

Donut Base Finetuned Kuzushiji

liked a dataset 9 months ago

naver-clova-ix/cord-v1

Viewer • Updated Jul 14, 2022 • 1k • 263 • 11

liked a model 9 months ago

naver-clova-ix/donut-base

Image-to-Text • Updated Aug 13, 2022 • 51.6k • 207

liked a model 10 months ago

microsoft/DialoGPT-medium

Text Generation • Updated Feb 29, 2024 • 270k • • 368

liked a dataset about 1 year ago

HuggingFaceFW/fineweb

Viewer • Updated Jan 31 • 25B • 836k • 2.12k

liked a model over 1 year ago

spacy/en_core_web_trf

Token Classification • Updated Jun 13, 2024 • 194 • 47

liked a model about 2 years ago

databricks/dolly-v2-12b

Text Generation • Updated Jun 30, 2023 • 3.45k • 1.96k