Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
19.4
TFLOPS
21
Mads
PRO
mhenrichsen
Follow
fhvilshoj's profile picture
lodrick-the-lafted's profile picture
AddiH's profile picture
43 followers
·
1 following
mhenrichsen
AI & ML interests
None yet
Recent Activity
replied
to
singhsidhukuldeep
's
post
13 days ago
Fascinating new research alert! Just read a groundbreaking paper on understanding Retrieval-Augmented Generation (RAG) systems and their performance factors. Key insights from this comprehensive study: >> Architecture Deep Dive The researchers analyzed RAG systems across 6 datasets (3 code-related, 3 QA-focused) using multiple LLMs. Their investigation revealed critical insights into four key design factors: Document Types Impact: • Oracle documents (ground truth) aren't always optimal • Distracting documents significantly degrade performance • Surprisingly, irrelevant documents boost code generation by up to 15.6% Retrieval Precision: • Performance varies dramatically by task • QA tasks need 20-100% retrieval recall • Perfect retrieval still fails up to 12% of the time on previously correct instances Document Selection: • More documents ≠ better results • Adding documents can cause errors on previously correct samples • Performance degradation increases ~1% per 5 additional documents in code tasks Prompt Engineering: • Most advanced prompting techniques underperform simple zero-shot prompts • Technique effectiveness varies significantly across models and tasks • Complex prompts excel at difficult problems but struggle with simple ones >> Technical Implementation The study utilized: • Multiple retrievers including BM25, dense retrievers, and specialized models • Comprehensive corpus of 70,956 unique API documents • Over 200,000 API calls and 1,000+ GPU hours of computation • Sophisticated evaluation metrics tracking both correctness and system confidence 💡 Key takeaway: RAG system optimization requires careful balancing of multiple factors - there's no one-size-fits-all solution.
replied
to
julien-c
's
post
13 days ago
After some heated discussion 🔥, we clarify our intent re. storage limits on the Hub TL;DR: - public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible - private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise) docs: https://huggingface.co./docs/hub/storage-limits We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community 🔥 cc: @reach-vb @pierric @victor and the HF team
new
activity
about 1 month ago
syvai/hviske-v2:
Tegnsætning og store bogstaver
View all activity
Organizations
spaces
2
Sort: Recently updated
Sleeping
🚀
Axolotl_Launcher
Runtime error
4
🚀
DanskGPT
models
13
Sort: Recently updated
mhenrichsen/gemma-2b-it
Text Generation
•
Updated
Feb 21
•
18
mhenrichsen/gemma-2b
Text Generation
•
Updated
Feb 21
•
357
•
1
mhenrichsen/gemma-7b-it
Text Generation
•
Updated
Feb 21
•
7
mhenrichsen/gemma-7b
Text Generation
•
Updated
Feb 21
•
1.24k
•
4
mhenrichsen/danskgpt-tiny-chat
Text Generation
•
Updated
Jan 27
•
39
•
12
mhenrichsen/hestenettetLM
Text Generation
•
Updated
Jan 16
•
784
•
3
mhenrichsen/danskgpt-tiny
Text Generation
•
Updated
Jan 13
•
3.11k
•
18
mhenrichsen/tinymix-8x1b
Text Generation
•
Updated
Jan 2
•
18
•
1
mhenrichsen/hviske
Automatic Speech Recognition
•
Updated
Dec 9, 2023
•
25
•
17
mhenrichsen/context-aware-splitter-1b-english
Text Generation
•
Updated
Nov 30, 2023
•
21
•
8
Expand 13 models
datasets
6
Sort: Recently updated
mhenrichsen/creator
Viewer
•
Updated
Dec 12, 2023
•
1k
•
38
mhenrichsen/context-aware-splits-english
Viewer
•
Updated
Nov 16, 2023
•
28k
•
47
•
5
mhenrichsen/hestenettet
Viewer
•
Updated
Nov 5, 2023
•
14.5k
•
49
•
3
mhenrichsen/terra
Viewer
•
Updated
Sep 27, 2023
•
25.4M
•
577
mhenrichsen/context-aware-splits
Viewer
•
Updated
Sep 17, 2023
•
12.3k
•
45
•
3
mhenrichsen/alpaca_2k_test
Viewer
•
Updated
Jul 22, 2023
•
2k
•
11.2k
•
25