Viet Anh Ta

darklord1611's activity

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

liked a dataset 3 days ago

ai-safety-institute/reward-hacking-sdf-default

Viewer • Updated Mar 30 • 68.4k • 28 • 1

upvoted a collection 5 days ago

(Some) Emergent Misalignment from Reward Hacking in RL

Collection

Model checkpoints from the project "(Some) Natural Emergent Misalignment from Reward Hacking in Non-Production RL" • 228 items • Updated 12 days ago • 5

upvoted a collection 26 days ago

Qwen-Scope

Collection

16 items • Updated 12 days ago • 66

liked a dataset about 1 month ago

lu-christina/assistant-axis-vectors

Updated Jan 22 • 2.07k • 8

upvoted an article about 1 month ago

view article

Article

Illustrating Reinforcement Learning from Human Feedback (RLHF)

• 
• 
• +2

natolambert, LouisCastricato, lvwerra, Dahoas

•

Dec 9, 2022

• 414

updated a model about 1 month ago

darklord1611/steerling-8b-em-bad-medical

Updated Apr 15

published a model about 1 month ago

darklord1611/steerling-8b-em-bad-medical

Updated Apr 15

updated a model about 2 months ago

darklord1611/steerling-8b-sft-tulu3-ckpt-6900

Updated Apr 10

published a model about 2 months ago

darklord1611/steerling-8b-sft-tulu3-ckpt-6900

Updated Apr 10

updated a dataset about 2 months ago

darklord1611/tulu-3-sft-mixture-english-clean

Viewer • Updated Apr 7 • 717k • 41

published a dataset about 2 months ago

darklord1611/tulu-3-sft-mixture-english-clean

Viewer • Updated Apr 7 • 717k • 41

upvoted an article 2 months ago

view article

Article

Uncensor any LLM with abliteration

• 

mlabonne

•

Jun 13, 2024

• 859

upvoted a collection 3 months ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.65k

liked a dataset 3 months ago

pminervini/HaluEval

Viewer • Updated Dec 7, 2023 • 64.5k • 8.26k • 28

liked a model 3 months ago

ByteDance/Ouro-1.4B

Text Generation • 1B • Updated Jan 18 • 55k • 96

upvoted a collection 3 months ago

Ouro

Collection

a family of pre-trained Looped Language Models. • 4 items • Updated Oct 29, 2025 • 32

liked a model 3 months ago

ByteDance/Ouro-1.4B-Thinking

Text Generation • 1B • Updated Feb 26 • 13.6k • 41

upvoted a collection 3 months ago

Open Character Training

Collection

https://arxiv.org/abs/2511.01689 • 8 items • Updated Nov 4, 2025 • 7

liked a model 3 months ago

tomg-group-umd/huginn-0125

Text Generation • Updated Jul 29, 2025 • 26.2k • 299

upvoted a collection 4 months ago

Alignment Pretraining (Geodesic, 2025): Data & Models

Collection

https://alignmentpretraining.ai — Read our paper for additional details about our data and models • 5 items • Updated Jan 16 • 7