Farouk PRO

pharaouk's activity

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

commented a paper 3 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2, 2025 • 187 •

7

New activity in pharaouk/dharma-2 over 1 year ago

Dataset can't be loaded as some outputs are ints (instead of strs)

3

#1 opened over 1 year ago by

UmerHA

fix: 2 questions from agieval were wrongly copied

1

#2 opened over 1 year ago by

UmerHA

New activity in allenai/peS2o almost 2 years ago

Update README.md

#7 opened almost 2 years ago by

pharaouk

New activity in SkunkworksAI/phi-2 about 2 years ago

model missing

7

#1 opened about 2 years ago by

barius

Add safetensors

1

#9 opened about 2 years ago by

jbochi

How do you run this?

5

#3 opened about 2 years ago by

alexweberk

Wrongly titled file?

👍 3

1

#6 opened about 2 years ago by

lemi99

Upload pytorch_model-00002-of-00002.bin

#2 opened about 2 years ago by

nisten

New activity in pharaouk/sentinel-7B about 2 years ago

Update tokenizer_config.json

#1 opened about 2 years ago by

Alignment-Lab-AI

New activity in open-llm-leaderboard/open_llm_leaderboard over 2 years ago

Can't submit model - migtissera/SynthIA-7B-v1.3

👍 2

16

#304 opened over 2 years ago by

migtissera

New activity in sileod/deberta-v3-large-tasksource-rlhf-reward-model over 2 years ago

Please share training code :)

1

#4 opened over 2 years ago by

pharaouk