David Golchinfar's picture

David Golchinfar PRO

DavidGF

·

https://vago-solutions.ai

AI & ML interests

finetune llms, improve german language understanding and generated text of llms

Recent Activity

liked a model about 22 hours ago

mradermacher/SauerkrautLM-Multi-ColBERT-33m-GGUF

liked a model 2 days ago

Qwen/Qwen3-4B-Thinking-2507

liked a model 2 days ago

Qwen/Qwen3-4B-Instruct-2507

View all activity

Organizations

upvoted a collection 6 days ago

SauerkrautLM-Multilingual-(Reason)-ColBERT

SauerkrautLM ColBERT is a suite of Late-Interaction retrieval models built with PyLate’s ColBERT architecture and tuned for seven European languages. • 7 items • Updated 6 days ago • 17

upvoted a collection 19 days ago

NER ITA

This collection presents my best models tailored for Named Entity Recognition (NER) tasks, exclusively designed for the Italian language. • 3 items • Updated 19 days ago • 2

upvoted 2 collections 3 months ago

Performance LLMs - Fine tuned

39 items • Updated Jun 6 • 6

Qwen3

84 items • Updated 2 days ago • 1.04k

upvoted a collection 4 months ago

Llama 4

Llama 4 release • 13 items • Updated Apr 29 • 602

upvoted an article 4 months ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

By

•

Mar 26

• 154

upvoted an article 5 months ago

Article

Open R1: Update #3

By

and 9 others •

Mar 11

• 295

upvoted 3 articles 7 months ago

Article

DeepSeek R1 on how to build conscious AGI

By

•

Jan 24

• 6

Article

Train 400x faster Static Embedding Models with Sentence Transformers

By

•

Jan 15

• 201

Article

The Large Language Model Course

By

•

Jan 16

• 199

upvoted an article 8 months ago

Article

Intelligence Potentiation: An Evolutionary Perspective on AI Agent Designs

By

•

Dec 19, 2024

• 4

upvoted an article 9 months ago

Article

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

By

•

Nov 9, 2024

• 9

upvoted a collection 9 months ago

🇫🇷 Calme-3

Here you can find all the new Calme-3 models • 27 items • Updated Feb 9 • 17

upvoted a paper 11 months ago

Spectrum: Targeted Training on Signal to Noise Ratio

Paper • 2406.06623 • Published Jun 7, 2024 • 14

upvoted an article about 1 year ago

Article

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

By

and 3 others •

Jul 31, 2024

• 60

upvoted 2 collections about 1 year ago

VAGO solutions quants

Quantized version for the excellent german speaking models created by VAGO solutions. • 6 items • Updated Apr 20, 2024 • 2

Qwen2

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 39 items • Updated 18 days ago • 368

upvoted a collection over 1 year ago

📀 Dataset comparison models

1.8B models trained on 350BT to compare different pretraining datasets • 8 items • Updated Jun 12, 2024 • 40

upvoted 2 articles over 1 year ago

Article

LLM Comparison/Test: Llama 3 Instruct 70B + 8B HF/GGUF/EXL2 (20 versions tested and compared!)

By

•

Apr 24, 2024

• 63

Article

Fine-tune Llama 3 with ORPO

By

•

Apr 22, 2024

• 239