Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
1
3
103
Vola Delta
hf-delta
Follow
shtefcs's profile picture
21world's profile picture
2 followers
·
31 following
AI & ML interests
LLM
Recent Activity
liked
a model
29 days ago
moonshotai/Kimi-Dev-72B
reacted
to
codelion
's
post
with 🔥
about 2 months ago
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?
updated
a dataset
2 months ago
hf-delta/market-data-npz
View all activity
Organizations
None yet
hf-delta
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
29 days ago
moonshotai/Kimi-Dev-72B
Text Generation
•
73B
•
Updated
28 days ago
•
19.2k
•
•
337
liked
4 models
4 months ago
teapotai/teapotllm
Text Generation
•
0.8B
•
Updated
Apr 19
•
223
•
179
rhymes-ai/Aria
Image-Text-to-Text
•
25B
•
Updated
Apr 23
•
24k
•
631
MBZUAI/LLMVoX
Text-to-Speech
•
Updated
Mar 16
•
8
•
49
sesame/csm-1b
Text-to-Speech
•
2B
•
Updated
May 27
•
30.1k
•
•
2.13k
liked
a model
5 months ago
convergence-ai/proxy-lite-3b
Image-to-Text
•
4B
•
Updated
Mar 8
•
1.2k
•
140
liked
2 models
7 months ago
mixedbread-ai/mxbai-embed-large-v1
Feature Extraction
•
0.3B
•
Updated
Mar 13
•
1.99M
•
•
699
Shakker-Labs/AWPortraitCN
Text-to-Image
•
Updated
Dec 4, 2024
•
196
•
211
liked
8 models
8 months ago
AIDC-AI/Ovis1.6-Gemma2-27B
Image-Text-to-Text
•
29B
•
Updated
Feb 26
•
49
•
63
mistralai/Mistral-Large-Instruct-2411
123B
•
Updated
Nov 19, 2024
•
14.1k
•
224
mistralai/Pixtral-Large-Instruct-2411
Image-Text-to-Text
•
Updated
Mar 16
•
418
Nexusflow/Athene-V2-Chat
Text Generation
•
73B
•
Updated
Nov 26, 2024
•
1.57k
•
•
294
Nexusflow/Athene-V2-Agent
Text Generation
•
73B
•
Updated
Nov 21, 2024
•
55
•
132
deepseek-ai/JanusFlow-1.3B
Any-to-Any
•
2B
•
Updated
Jan 27
•
1.25k
•
147
ali-vilab/In-Context-LoRA
Text-to-Image
•
Updated
Dec 17, 2024
•
4.25k
•
•
620
renderartist/retrocomicflux
Text-to-Image
•
Updated
Nov 8, 2024
•
968
•
•
38
liked
4 models
9 months ago
genmo/mochi-1-preview
Text-to-Video
•
Updated
Dec 18, 2024
•
13.9k
•
•
1.24k
amphion/MaskGCT
Text-to-Speech
•
Updated
Apr 13
•
78
•
•
295
Freepik/flux.1-lite-8B-alpha
Text-to-Image
•
Updated
Dec 30, 2024
•
1.6k
•
•
421
dataautogpt3/Proteus-v0.6
Text-to-Image
•
Updated
Oct 18, 2024
•
101
•
15
Load more