Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
2
7
11
Choi Jaehun
Ash-Hun
Follow
21world's profile picture
uvamba's profile picture
msfjung's profile picture
7 followers
·
16 following
https://github.com/ash-hun
ash-hun
choijaehun
AI & ML interests
LLM, RAG, Agent, GenAI, Modeling for RAG
Recent Activity
liked
a dataset
5 days ago
open-thoughts/OpenThoughts-114k
liked
a Space
23 days ago
maum-ai/KOFFVQA-Leaderboard
reacted
to
singhsidhukuldeep
's
post
with 🔥
3 months ago
Exciting breakthrough in LLM reasoning: Introducing "Thread of Thought" (ThoT) - a novel prompting strategy that revolutionizes how language models handle chaotic contexts! Unlike traditional approaches that struggle with complex, interleaved information, ThoT enables LLMs to methodically segment and analyze extended contexts with remarkable precision. Here's how it works: Technical Deep Dive: - ThoT employs a two-step prompting mechanism: 1. Initial Analysis: Uses a template combining chaotic context (X) and query (Q) with a trigger sentence that initiates systematic reasoning. 2. Conclusion Refinement: Leverages the organized thought sequence to extract definitive answers. Implementation Details: - Seamlessly integrates as a "plug-and-play" module with existing LLMs. - Requires no model retraining or fine-tuning. - Works with various prompting techniques and model architectures. Performance Highlights: - Outperformed traditional methods on PopQA and EntityQ datasets. - Achieved 57.4% accuracy with GPT-3.5-turbo (vs. 48.2% for Chain-of-Thought). - Demonstrated superior performance across model scales, from 7B to 70B parameters. Key Applications: - Retrieval-augmented generation. - Multi-turn conversation responses. - Complex reasoning tasks requiring information synthesis. What makes it special: ThoT mirrors human cognitive processes by breaking down complex information into manageable segments while maintaining logical continuity – a game-changer for handling information-dense contexts.
View all activity
Organizations
Ash-Hun
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
liked
a dataset
5 days ago
open-thoughts/OpenThoughts-114k
Viewer
•
Updated
6 days ago
•
114k
•
14.2k
•
229
liked
a Space
23 days ago
Running
6
🏆
KOFFVQA Leaderboard
liked
2 datasets
4 months ago
KingNish/reasoning-base-20k
Viewer
•
Updated
Oct 5, 2024
•
19.9k
•
2.06k
•
207
MarkrAI/KoCommercial-Dataset
Viewer
•
Updated
Mar 22, 2024
•
175k
•
433
•
138
liked
a dataset
10 months ago
maywell/ko_Ultrafeedback_binarized
Viewer
•
Updated
Nov 9, 2023
•
62k
•
90
•
30
liked
2 models
11 months ago
beomi/gemma-ko-7b
Text Generation
•
Updated
Mar 26, 2024
•
4.21k
•
46
google/gemma-7b
Text Generation
•
Updated
Jun 27, 2024
•
72k
•
•
3.11k
liked
3 models
12 months ago
mlx-community/CodeLlama-70b-Python-hf-4bit-MLX
Text Generation
•
Updated
Jan 30, 2024
•
25
•
11
Ash-Hun/WelSSiSKo_v3_llama-2-ko-base_text-generation
Text Generation
•
Updated
Mar 8, 2024
•
9
•
1
allenai/OLMo-7B
Text Generation
•
Updated
Jul 16, 2024
•
25.6k
•
629
liked
a model
about 1 year ago
monologg/koelectra-base-v3-finetuned-korquad
Question Answering
•
Updated
Jun 12, 2023
•
743
•
4