Sayhan Yalvaçer

sayhan's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

liked a Space 1 day ago

Running

34

🦀

Gemini Coder

upvoted a collection 15 days ago

Performance LLMs - Fine tuned

Collection

21 items • Updated 15 days ago • 5

liked 2 models 2 months ago

lmstudio-community/aya-expanse-32b-GGUF

Text Generation • Updated Oct 24 • 264 • 3

CohereForAI/aya-expanse-32b

Text Generation • Updated 19 days ago • 22.7k • 193

liked 2 models 3 months ago

deepseek-ai/DeepSeek-V2.5

Text Generation • Updated 14 days ago • 13.8k • 679

mistral-community/pixtral-12b-240910

Image-Text-to-Text • Updated Oct 1 • 383

liked 7 models 5 months ago

Qwen/Qwen2-Math-72B-Instruct

Text Generation • Updated Sep 13 • 604 • 87

migtissera/Tess-3-Llama-3.1-405B

Updated Aug 15 • 129 • 44

google/gemma-2-2b-it

Text Generation • Updated Aug 27 • 405k • • 807

Nexusflow/Athene-70B

Text Generation • Updated Nov 15 • 7.52k • 193

meta-llama/Llama-3.1-8B-Instruct

Text Generation • Updated Sep 25 • 4.51M • • 3.32k

mistralai/Mistral-Large-Instruct-2407

Updated Oct 16 • 2.95M • 812

mistralai/Mistral-Nemo-Instruct-2407

Text Generation • Updated Nov 6 • 3.1M • • 1.32k

liked a model 7 months ago

mistralai/Codestral-22B-v0.1

Text Generation • Updated Jul 31 • 2.95M • 1.17k

upvoted a paper 7 months ago

Transformers Can Do Arithmetic with the Right Embeddings

Paper • 2405.17399 • Published May 27 • 52

liked 2 models 7 months ago

openchat/openchat-3.6-8b-20240522

Text Generation • Updated May 28 • 16.4k • 152

NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF

Updated May 14 • 9.74k • 84

liked a dataset 7 months ago

TIGER-Lab/MMLU-Pro

Viewer • Updated 28 days ago • 12.1k • 38.7k • 302

reacted to DmitryRyumin's post with 🔥 8 months ago

view post

Post

2179

🔥🚀🌟 New Research Alert - xLSTM! 🌟🚀🔥
📄 Title: xLSTM: Extended Long Short-Term Memory 🔝

📝 Description: xLSTM is a scaled-up LSTM architecture with exponential gating and modified memory structures to mitigate known limitations. xLSTM blocks outperform SOTA transformers and state-space models in performance and scaling.

👥 Authors: Maximilian Beck et al.

📄 Paper: xLSTM: Extended Long Short-Term Memory (2405.04517)

📁 Repository: https://github.com/NX-AI/xlstm

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #xLSTM #DeepLearning #Innovation #AI

• 
• 

• 
• 1 reply

·

🔥

18

18

👍

4

4

+

Reply

liked a model 8 months ago

ddh0/Meta-Llama-3-8B-Instruct-bf16-GGUF

Text Generation • Updated May 10 • 801 • 44