nyuuzyou/Minecraft-Skins-20M
Updated
nyuuzyou
nyuuzyou
AI & ML interests
None yet
Recent Activity
updated
a dataset
3 minutes ago
nyuuzyou/Minecraft-Skins-20M
published
a dataset
8 minutes ago
nyuuzyou/azkurs
updated
a dataset
11 minutes ago
nyuuzyou/azkurs
Organizations
nyuuzyou's activity
updated
a
dataset
3 minutes ago
published
a
dataset
8 minutes ago
updated
a
dataset
11 minutes ago
Cannot decode some lines
1
#1 opened 4 days ago
by
KaraKaraWitch
updated
a
dataset
20 minutes ago
published
a
dataset
39 minutes ago
liked
a
dataset
4 days ago
reacted to
codelion's
post with 🔥
5 days ago
Post
2298
Introducing AutoThink: Adaptive reasoning for LLMs that improves performance by 43% on reasoning benchmarks!
Instead of using fixed thinking budgets, AutoThink:
- Classifies query complexity (HIGH/LOW) using adaptive classification
- Dynamically allocates thinking tokens based on complexity
- Uses steering vectors derived from Pivotal Token Search to guide reasoning patterns
Results on DeepSeek-R1-Distill-Qwen-1.5B:
- GPQA-Diamond: 31.06% vs 21.72% baseline (+9.34 points)
- MMLU-Pro: 26.38% vs 25.58% baseline (+0.8 points)
- Uses fewer tokens than baseline approaches
Works with any local reasoning model - DeepSeek, Qwen, Llama, custom models. The technique combines our research on Pivotal Token Search (PTS) implementation and adaptive classification frameworks.
Paper: AutoThink: efficient inference for reasoning LLMs
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5253327
Code and examples:
https://github.com/codelion/optillm/tree/main/optillm/autothink
PTS implementation and technical details:
https://github.com/codelion/pts
https://huggingface.co/blog/codelion/pts
Adaptive classifier framework:
https://github.com/codelion/adaptive-classifier
Would love to hear your thoughts on adaptive resource allocation for LLM reasoning! Have you experimented with similar approaches?
Instead of using fixed thinking budgets, AutoThink:
- Classifies query complexity (HIGH/LOW) using adaptive classification
- Dynamically allocates thinking tokens based on complexity
- Uses steering vectors derived from Pivotal Token Search to guide reasoning patterns
Results on DeepSeek-R1-Distill-Qwen-1.5B:
- GPQA-Diamond: 31.06% vs 21.72% baseline (+9.34 points)
- MMLU-Pro: 26.38% vs 25.58% baseline (+0.8 points)
- Uses fewer tokens than baseline approaches
Works with any local reasoning model - DeepSeek, Qwen, Llama, custom models. The technique combines our research on Pivotal Token Search (PTS) implementation and adaptive classification frameworks.
Paper: AutoThink: efficient inference for reasoning LLMs
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5253327
Code and examples:
https://github.com/codelion/optillm/tree/main/optillm/autothink
PTS implementation and technical details:
https://github.com/codelion/pts
https://huggingface.co/blog/codelion/pts
Adaptive classifier framework:
https://github.com/codelion/adaptive-classifier
Would love to hear your thoughts on adaptive resource allocation for LLM reasoning! Have you experimented with similar approaches?
- 5 replies
reacted to
ProCreations's
post with 🚀
6 days ago
Post
2852
Eyyyy 50 followers 🤯
- 1 reply
replied to
jasoncorkill's
post
7 days ago
I'm not sure if this is it, but it looks like it's already available
https://huggingface.co/datasets/Rapidata/text-2-video-human-preferences-veo3
https://huggingface.co/datasets/Rapidata/1k-ranked-videos-coherence
published
a
model
8 days ago
updated
a
model
8 days ago
published
a
model
8 days ago
updated
2
models
8 days ago
Comment here to check which of your fics were included - SOME ARCHIVE-LOCKED FICS WERE SCRAPED
❤️
16
135
#213 opened about 1 month ago
by
nothankies
posted
an
update
10 days ago
Post
2900
I recently updated
nyuuzyou/pxhere dataset and it now contains approximately 1.1M CC0 high-resolution images
updated
a
dataset
10 days ago
published
a
dataset
10 days ago
updated
a
dataset
10 days ago