Mads PRO

mhenrichsen

mhenrichsen

AI & ML interests

None yet

Recent Activity

replied to singhsidhukuldeep's post 25 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 25 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

mhenrichsen's activity

New activity in syvai/hviske-v2 about 1 month ago

Tegnsætning og store bogstaver

#2 opened about 2 months ago by

RasmusKlett

New activity in mhenrichsen/DanskGPT about 2 months ago

Runtime error her på HuggingFace

#1 opened about 2 months ago by

borup

New activity in syvai/translator-v1 2 months ago

Better than gpt-4o on what benchmark/dataset?

#1 opened 2 months ago by

mathiasn1

New activity in syvai/hviske-v2 3 months ago

Mindre rettelser

#1 opened 3 months ago by

KennethEnevoldsen

New activity in webbigdata/C3TR-Adapter 5 months ago

License?

#2 opened 5 months ago by

mhenrichsen

New activity in mhenrichsen/danskgpt-tiny-chat 7 months ago

How to convert the model to a gguf model?

#3 opened 9 months ago by

pksorensen

New activity in syvai/llama3-da-base 8 months ago

Adding `safetensors` variant of this model

#1 opened 8 months ago by

SFconvertbot

New activity in meta-llama/Meta-Llama-3-8B 9 months ago

Generated text is garbled?

#53 opened 9 months ago by

gbhall

New activity in HuggingFaceFW/fineweb 9 months ago

Split by languages?

#7 opened 9 months ago by

mhenrichsen

New activity in google/gemma-7b 11 months ago

license?

#9 opened 11 months ago by

mhenrichsen

New activity in mhenrichsen/hestenettetLM 12 months ago

Adding `safetensors` variant of this model

#1 opened 12 months ago by

SFconvertbot

New activity in mhenrichsen/danskgpt-tiny-chat 12 months ago

Adding `safetensors` variant of this model

#1 opened 12 months ago by

SFconvertbot

New activity in mhenrichsen/danskgpt-tiny 12 months ago

Adding `safetensors` variant of this model

#1 opened 12 months ago by

SFconvertbot

New activity in TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T about 1 year ago

Adding `safetensors` variant of this model

#4 opened about 1 year ago by

mhenrichsen

New activity in mhenrichsen/hviske about 1 year ago

Cannot load model

#1 opened about 1 year ago by

andersgb1

json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

#2 opened about 1 year ago by

FTTF

Training parameters and training setup?

#3 opened about 1 year ago by

ymir95

New activity in mhenrichsen/context-aware-splitter-1b over 1 year ago

Adding `safetensors` variant of this model

#1 opened over 1 year ago by

SFconvertbot