Şuayp Talha Kocabay's picture

Şuayp Talha Kocabay PRO

suayptalha

·

https://discord.com/users/suaypt

AI & ML interests

NLP, LLMs, Transformers, Merging, RNNs, CNNs, ANNs, Computer Vision and ML algorithms

Recent Activity

liked a model about 7 hours ago

sometimesanotion/Qwen2.5-7B-Gordion-v0.1-Prose

updated a model about 12 hours ago

suayptalha/Clarus-7B-v0.3

liked a model about 13 hours ago

suayptalha/Clarus-7B-v0.3

View all activity

Organizations

Posts 5

Post

636

I've just distilled Llama-3.2-3B-Instruct with deepseek-ai/DeepSeek-R1 on ServiceNow-AI/R1-Distill-SFT dataset. 🐋🦙

Here is the model:
suayptalha/DeepSeek-R1-Distill-Llama-3B

Post

1867

My last Falcon3-7B merge model, suayptalha/Falcon3-Jessi-v0.4-7B-Slerp, is currently ranked #1 on the open-llm-leaderboard/open_llm_leaderboard among all models with up to 14B parameters.
My Qwen2.5-7B merge model, suayptalha/HomerCreativeAnvita-Mix-Qw7B, is also ranked #7, placing two of my models in the top 10!

Collections 6

spaces 4

QwQ-32B-Preview-Vision

QwQ-32B-Preview with Vision 👁

Chat With Komodo

Chat with Komodo Models 🦎

Chat With FastLlama

Chat with FastLlama Models 🦙

YOLO World

models 37

suayptalha/Clarus-7B-v0.3

Text Generation • Updated about 12 hours ago • 2

suayptalha/Clarus-7B-v0.1

Text Generation • Updated 2 days ago • 718 • 4

suayptalha/Clarus-7B-v0.2

Text Generation • Updated 2 days ago • 54 • 3

suayptalha/DeepSeek-R1-Distill-Llama-3B

Text Generation • Updated 2 days ago • 131 • 3

suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0

Text Generation • Updated 5 days ago • 35 • 2

suayptalha/Luminis-phi-4

Text Generation • Updated 6 days ago • 1.57k • 9

suayptalha/ClimateLlama-8B-TR

Text Generation • Updated 11 days ago • 36 • 3

suayptalha/ClimateLlama-8B

Text Generation • Updated 12 days ago • 76 • 3

suayptalha/Lamarckvergence-14B

Text Generation • Updated 14 days ago • 1.24k • 16

suayptalha/Qwenhancement-32B-v1

Text Generation • Updated 17 days ago • 27 • 2

datasets 1

suayptalha/Poetry-Foundation-Poems

Viewer • Updated Dec 22, 2024 • 13.9k • 108 • 5