Hugging Face's logo
Dimitris Roussis's picture
15 9 91

Dimitris Roussis

droussis
PetrosStav's profile picture dnna's profile picture christinacdl's profile picture
·
https://www.ilsp.gr/en/members/roussis-dimitris/

AI & ML interests

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

Recent Activity

upvoted a paper 1 day ago
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
updated a dataset 12 days ago
ilsp/m-ArenaHard_greek
liked a dataset 12 days ago
ilsp/m-ArenaHard_greek
View all activity

Organizations

Institute for Language and Speech Processing's profile picture

droussis's activity

New activity in ilsp/Llama-Krikri-8B-Instruct 16 days ago

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

6
#2 opened 16 days ago by
Ptrnk
New activity in ilsp/Llama-Krikri-8B-Instruct 17 days ago

Seems very promising

3
#1 opened 18 days ago by
gstrat88
New activity in lightblue/rag_multilingual_training_negatives 4 months ago

Is this the same as Kurage?

2
#2 opened 4 months ago by
droussis
New activity in utter-project/EuroLLM-1.7B-Instruct 5 months ago

Context extension?

1
#4 opened 5 months ago by
droussis
New activity in PleIAs/Greek-PD 6 months ago

Dataset fails loading
#2 opened 6 months ago by
droussis
New activity in PleIAs/WTO-Text 7 months ago

Dataset fails loading
#1 opened 7 months ago by
droussis
New activity in bitextor/bicleaner-ai-full-large-en-xx 10 months ago

About context size and difference in quality

3
#1 opened 10 months ago by
droussis
New activity in ilsp/Meltemi-7B-v1 10 months ago

Future plans (Llama 3?)

1
#3 opened 10 months ago by
velocity
New activity in ilsp/Meltemi-7B-Instruct-v1 11 months ago

LLama-Factory inference issue

14
#2 opened 11 months ago by
ianss
New activity in CausalLM/GPT-4-Self-Instruct-Greek about 1 year ago

Regarding quality assessment

2
#1 opened about 1 year ago by
droussis
New activity in CausalLM/GPT-4-Self-Instruct-German about 1 year ago

Community request: more languages

8
#1 opened about 1 year ago by
emre
New activity in Intel/neural-chat-dataset-v2 over 1 year ago

Which part of HC3?
#1 opened over 1 year ago by
droussis
New activity in meta-math/MetaMathQA-40K over 1 year ago

Difference between 40K and 395K dataset
#2 opened over 1 year ago by
droussis
New activity in Helsinki-NLP/opus-mt-tc-big-en-pt over 1 year ago

The model output is totally corrupted

4
#5 opened over 1 year ago by
fernandofernandes
New activity in Helsinki-NLP/opus-tatoeba-en-ja over 1 year ago

Fix weights by putting the right value in `lm_head.weight`

3
#3 opened over 1 year ago by
sgugger
New activity in Helsinki-NLP/opus-mt-tc-big-en-pt over 1 year ago

The model output is totally corrupted

4
#5 opened over 1 year ago by
fernandofernandes