xai-org/grok-2
Updated • 43.1k • 1.09k
AI & ML interests
Understand the universe
LilyGrok
updated a
model 6 months ago
Update README.md
🚀 1
3
#1 opened 9 months ago
by 
jeffhj
lmzheng
updated a
model 9 months ago
lmzheng
published a
model 9 months ago
Update README.md
🚀 1
3
#1 opened 9 months ago
by jeffhj
yuchenlin
authored 2
papers about 1 year ago
yuchenlin
authored 2
papers over 1 year ago
yuchenlin
authored 5
papers almost 2 years ago
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Paper • 2406.18495 • Published • 13
MantisScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation
Paper • 2406.15252 • Published • 18
WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
Paper • 2406.11069 • Published • 14
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Paper • 2406.08464 • Published • 72
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
Paper • 2406.04770 • Published • 28
Post
4823
Introducing **BaseChat**!
https://huggingface.co/spaces/allenai/BaseChat_URIAL
This is a demo for our URIAL paper that enables base LLMs to chat with in-context alignment. You can talk directly with base, untuned LLMs to find out what knowledge and skills they have already learned from pre-training instead of SFT or xPO or RLHF. Also, you can use this to explore the pre-training data of base LLMs by chatting! I found a very interesting case: Base version of Llama-3-8B often thinks it is built by OpenAI, lol.
https://huggingface.co/spaces/allenai/BaseChat_URIAL
This is a demo for our URIAL paper that enables base LLMs to chat with in-context alignment. You can talk directly with base, untuned LLMs to find out what knowledge and skills they have already learned from pre-training instead of SFT or xPO or RLHF. Also, you can use this to explore the pre-training data of base LLMs by chatting! I found a very interesting case: Base version of Llama-3-8B often thinks it is built by OpenAI, lol.
yuchenlin
authored a
paper about 2 years ago
liuhaotian
updated a
dataset about 2 years ago
szymonxai
updated a
model about 2 years ago
yuchenlin
authored 2
papers about 2 years ago