19 12 93

Dimitris Roussis

droussis

https://www.ilsp.gr/en/members/roussis-dimitris/

AI & ML interests

All things data for LLMs, NMT, evaluation, safety, alignment, and more

Recent Activity

new activity about 15 hours ago

driaforall/verifiable-pythonic-function-calling-lite:Have you verified the answers?

upvoted a paper 1 day ago

reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs

new activity 3 days ago

Jofthomas/hermes-function-calling-thinking-V1:Thinking token generation

View all activity

Organizations

droussis's activity

New activity in driaforall/verifiable-pythonic-function-calling-lite about 15 hours ago

Have you verified the answers?

#2 opened about 15 hours ago by

droussis

upvoted a paper 1 day ago

reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs

Paper • 2503.11751 • Published 6 days ago • 15

New activity in Jofthomas/hermes-function-calling-thinking-V1 3 days ago

Thinking token generation

#2 opened 23 days ago by

thtang

upvoted an article 8 days ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

9 days ago

• 323

updated 2 models 9 days ago

ilsp/Llama-Krikri-8B-Instruct-GGUF

Text Generation • Updated 5 days ago • 889 • 8

ilsp/Llama-Krikri-8B-Instruct

Text Generation • Updated 9 days ago • 2.69k • 17

New activity in OpenLeecher/lmsys_chat_1m_clean 12 days ago

What is the accuracy of the Skywork/Skywork-Reward-Gemma-2-27B-v0.2? How much is the correct sample of 273K?

#5 opened 2 months ago by

ShelterW

liked a dataset 12 days ago

FuseAI/FuseChat-3.0-SFT-Data

Viewer • Updated Feb 7 • 94.5k • 161 • 1

New activity in Qwen/QwQ-32B 13 days ago

What languages were you trained in?

#7 opened 15 days ago by

NickyNicky

liked a dataset 14 days ago

WiroAI/dolphin-r1-turkish

Viewer • Updated 14 days ago • 108k • 42 • 11

upvoted a paper 14 days ago

Can LLMs Predict Citation Intent? An Experimental Analysis of In-context Learning and Fine-tuning on Open LLMs

Paper • 2502.14561 • Published 28 days ago • 2

updated a model 15 days ago

ilsp/Llama-Krikri-8B-Base

Text Generation • Updated 15 days ago • 236 • 10

upvoted a paper 21 days ago

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Paper • 2502.18449 • Published 23 days ago • 70

updated a dataset about 1 month ago

ilsp/m-ArenaHard_greek

Viewer • Updated Feb 17 • 1k • 106 • 1

liked a dataset about 1 month ago

ilsp/m-ArenaHard_greek

Viewer • Updated Feb 17 • 1k • 106 • 1

published a dataset about 1 month ago

ilsp/m-ArenaHard_greek

Viewer • Updated Feb 17 • 1k • 106 • 1

liked a model about 1 month ago

ilsp/Llama-Krikri-8B-Instruct-GGUF

Text Generation • Updated 5 days ago • 889 • 8

upvoted a paper about 1 month ago

Weighted-Reward Preference Optimization for Implicit Model Fusion

Paper • 2412.03187 • Published Dec 4, 2024 • 12

New activity in ilsp/Llama-Krikri-8B-Instruct about 1 month ago

Bug on the tokenizer, using the code that you provided for the inference.

#2 opened about 1 month ago by

Ptrnk

Seems very promising

#1 opened about 1 month ago by

gstrat88

Dimitris Roussis

AI & ML interests

Recent Activity

Organizations

droussis's activity

Have you verified the answers?

Thinking token generation

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

What is the accuracy of the Skywork/Skywork-Reward-Gemma-2-27B-v0.2? How much is the correct sample of 273K?

What languages ​​were you trained in?

Bug on the tokenizer, using the code that you provided for the inference.

Seems very promising

What languages were you trained in?