Hugging Face's logo
Peter Szemraj's picture
422 35 800

Peter Szemraj PRO

pszemraj
21world's profile picture amckenna's profile picture thomastay's profile picture
·
https://pszemraj.carrd.co/

AI & ML interests

metallic intuition

Organizations

Stacked Summaries's profile picture Analytics Club at ETH Zürich's profile picture ml4pubmed's profile picture Gradio-Blocks-Party's profile picture OneFrame's profile picture postbot's profile picture Ontocord's M*DEL's profile picture BEEspoke Data's profile picture Sablo AI's profile picture memecaps's profile picture Hugging Face Discord Community's profile picture

pszemraj's activity

New activity in open-llm-leaderboard/open_llm_leaderboard 7 days ago

flan-t5 evals failing

1
#898 opened 7 days ago by pszemraj
New activity in pszemraj/long-t5-tglobal-base-16384-book-summary 22 days ago

Output is nonsensical

4
#22 opened 23 days ago by matthew-at-qamcom
New activity in argilla/magpie-ultra-v0.1 26 days ago

dataset topic diversity

3
#2 opened 29 days ago by pszemraj
commented a paper about 1 month ago
New activity in BEE-spoke-data/Meta-Llama-3-8Bee about 1 month ago

Adding Evaluation Results
#1 opened about 1 month ago by leaderboard-pr-bot
New activity in pszemraj/Llama-3-6.3b-v0.1 about 1 month ago

Adding Evaluation Results
#2 opened about 1 month ago by leaderboard-pr-bot
New activity in pszemraj/Mistral-v0.3-6B about 1 month ago

Adding Evaluation Results
#2 opened about 1 month ago by leaderboard-pr-bot
New activity in BEE-spoke-data/smol_llama-220M-GQA-fineweb_edu about 1 month ago

Adding Evaluation Results
#1 opened about 1 month ago by leaderboard-pr-bot
New activity in OpenCo7/UpVoteWeb about 2 months ago

does this contain posts?

3
#4 opened about 2 months ago by pszemraj
New activity in pszemraj/long-t5-tglobal-xl-16384-booksci-summary-v1 about 2 months ago

new dataset

1
#1 opened about 2 months ago by Recognizeme
New activity in open-llm-leaderboard/open_llm_leaderboard about 2 months ago

WizardLM-8x22B Evaluation failed

25
#823 opened about 2 months ago by llama-anon
New activity in pszemraj/SHP-2-dpo-100k_sample 2 months ago

Librarian Bot: Add dpo tag
#2 opened 2 months ago by librarian-bot
New activity in BEE-spoke-data/smol_llama-220M-GQA 2 months ago

Adding Evaluation Results
#2 opened 2 months ago by leaderboard-pr-bot
New activity in HuggingFaceFW/fineweb-edu-classifier 3 months ago

fix example code

1
#2 opened 3 months ago by pszemraj
New activity in pszemraj/Llama-3-6.3b-v0.1 3 months ago

Excellent Approach

2
#1 opened 3 months ago by 1littlecoder
New activity in pszemraj/Mistral-v0.3-6B 3 months ago

Adding Evaluation Results
#1 opened 3 months ago by leaderboard-pr-bot
New activity in open-llm-leaderboard/open_llm_leaderboard 4 months ago

ALL Jamba models failing

17
#690 opened 4 months ago by devingulliver
New activity in BEE-spoke-data/beeweb-5k 4 months ago

Librarian Bot: Add language metadata for dataset

1
#1 opened 4 months ago by librarian-bot
New activity in EleutherAI/pile-t5-large 5 months ago

why UMT5

6
#1 opened 5 months ago by pszemraj
New activity in BEE-spoke-data/smol_llama-101M-GQA 5 months ago

Link to code repository

1
#3 opened 5 months ago by ewre324
New activity in BEE-spoke-data/smol_llama-220M-openhermes 5 months ago

What is the model architecture?

1
#2 opened 5 months ago by ewre324
New activity in amazingvince/Not-WizardLM-2-7B 5 months ago

add link to colab example
#1 opened 5 months ago by pszemraj
New activity in pszemraj/distill-pegasus-CompMath 5 months ago

Librarian Bot: Update Hugging Face dataset ID
#3 opened 5 months ago by librarian-bot
New activity in pszemraj/qmsum-cleaned 5 months ago

Empty test cases

2
#2 opened 5 months ago by StDestiny
New activity in ethzanalytics/blip2-flan-t5-xl-sharded 5 months ago

Adding `safetensors` variant of this model
#1 opened 5 months ago by SFconvertbot
New activity in pszemraj/led-large-book-summary 5 months ago

Hardware requirements

1
#19 opened 5 months ago by Arunmass
New activity in ai21labs/Jamba-v0.1 5 months ago

Jambaleo
#10 opened 5 months ago by pszemraj
New activity in BEE-spoke-data/allNLI-sbert 5 months ago

Librarian Bot: Add language metadata for dataset
#2 opened 5 months ago by librarian-bot
New activity in BEE-spoke-data/gutenberg-en-v1-clean 5 months ago

[bot] Conversion to Parquet

1
#1 opened 5 months ago by parquet-converter
New activity in postbot/gpt-neo-1.3B-emailgen 6 months ago

Adding Evaluation Results
#2 opened 6 months ago by leaderboard-pr-bot
New activity in pszemraj/distilgpt2-HC3 6 months ago

Adding Evaluation Results
#3 opened 6 months ago by leaderboard-pr-bot
New activity in BEE-spoke-data/smol_llama-220M-openhermes 6 months ago

Adding Evaluation Results
#1 opened 6 months ago by leaderboard-pr-bot
New activity in BEE-spoke-data/NanoLlama-GQA-L10-A32_KV8-v13-KI 6 months ago

Adding Evaluation Results
#1 opened 6 months ago by leaderboard-pr-bot
New activity in BEE-spoke-data/TinyLlama-3T-1.1bee 6 months ago

Adding Evaluation Results
#1 opened 6 months ago by leaderboard-pr-bot
New activity in BEE-spoke-data/smol_llama-220M-open_instruct 6 months ago

Adding Evaluation Results
#1 opened 6 months ago by leaderboard-pr-bot
New activity in BEE-spoke-data/smol_llama-220M-GQA 6 months ago

Adding Evaluation Results
#1 opened 6 months ago by leaderboard-pr-bot
New activity in pszemraj/flan-t5-xl-grammar-synthesis 6 months ago

Repeated text leads to ~infinite processing

4
#3 opened 6 months ago by Ejentos
New activity in pszemraj/flan-t5-large-grammar-synthesis 6 months ago

determining and formatting according to specific tone during generation of text.

1
#15 opened 7 months ago by AgVishal25

AttributeError: 'T5LayerFF' object has no attribute 'config'

1
#12 opened about 1 year ago by Tommycmy
New activity in pszemraj/pegasus-x-large-book-summary 7 months ago

Billsum Evaluation

1
#6 opened almost 2 years ago by mlkorra
New activity in TuringsSolutions/NYTWritingStyleGuide 7 months ago

Rename Main to data.json

3
#1 opened 8 months ago by davanstrien
commented a paper 8 months ago
New activity in upstage/SOLAR-10.7B-v1.0 8 months ago

Data for Continued Pre-Training

6
#8 opened 8 months ago by pszemraj
New activity in pszemraj/long-t5-tglobal-base-16384-book-summary 8 months ago

Not able to test it.

2
#21 opened 8 months ago by JESUSCOLIN
New activity in pszemraj/electra-small-discriminator-CoLA 9 months ago

Librarian Bot: Add base_model information to model

1
#1 opened 9 months ago by librarian-bot
New activity in pszemraj/mGPT-Peter-mwe 9 months ago

Librarian Bot: Add base_model information to model

1
#2 opened 9 months ago by librarian-bot
New activity in pszemraj/gpt-neo-125M-magicprompt-SD 9 months ago

Librarian Bot: Add base_model information to model

1
#2 opened 9 months ago by librarian-bot
New activity in pszemraj/opt-peter-2.7B 9 months ago

Librarian Bot: Add base_model information to model

1
#4 opened 9 months ago by librarian-bot
New activity in pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13 9 months ago

Librarian Bot: Add base_model information to model

1
#8 opened 9 months ago by librarian-bot
New activity in pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP14 9 months ago

Librarian Bot: Add base_model information to model

1
#4 opened 9 months ago by librarian-bot
New activity in pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP17 9 months ago

Librarian Bot: Add base_model information to model

1
#5 opened 9 months ago by librarian-bot
New activity in postbot/emailgen-pythia-410m-deduped 9 months ago

Librarian Bot: Add base_model information to model

1
#5 opened 9 months ago by librarian-bot
New activity in postbot/gpt-neo-1.3B-emailgen 9 months ago

Librarian Bot: Add base_model information to model

1
#1 opened 9 months ago by librarian-bot
New activity in postbot/t5-base-kw2email-v4 9 months ago

Librarian Bot: Add base_model information to model

1
#1 opened 9 months ago by librarian-bot
New activity in pszemraj/flan-t5-large-grammar-synthesis 9 months ago

Grammar explanation

2
#14 opened 9 months ago by Ejentos
New activity in jbochi/coedit-base 9 months ago

cc-by-nc vs dataset license

2
#1 opened 9 months ago by pszemraj
New activity in BEE-spoke-data/smol_llama-101M-GQA 9 months ago

GPU used for training

1
#2 opened 9 months ago by Locutusque
New activity in jinaai/jina-embeddings-v2-base-en 9 months ago

Is there a ETA for large version?

6
#31 opened 9 months ago by kk3dmax
New activity in pszemraj/led-large-book-summary 9 months ago

Upload Roulstone et al 2015 PGfAR Library final.pdf

1
#18 opened 9 months ago by Seyma-ccl
New activity in abidlabs/GPT-Baker 9 months ago

Adding youtube video knoweledge to GPT's

1
#8 opened 9 months ago by ii5