Hugging Face's logo
Eldar Kurtic's picture
14 4 2

Eldar Kurtic

ekurtic
21world's profile picture rgreenberg1's profile picture rahulsinghal's profile picture
·

AI & ML interests

Compression of deep neural networks

Recent Activity

updated a model 1 day ago
neuralmagic/Sparse-Llama-3.1-8B-2of4
upvoted a paper 16 days ago
commented a paper 16 days ago

Organizations

Neural Magic's profile picture IST Austria Distributed Algorithms and Systems Lab's profile picture NM Testing's profile picture ISTA DASLab Testing Account's profile picture

ekurtic's activity

commented a paper 16 days ago
New activity in neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic 17 days ago

Context length

4
#2 opened 18 days ago by galigator
New activity in open-llm-leaderboard/open_llm_leaderboard about 2 months ago

Normalization for MMLU-Pro doesn't make sense

11
#947 opened about 2 months ago by ekurtic
New activity in TIGER-Lab/MMLU-Pro about 2 months ago

Paper claims there are 10-choices but the test split has varying number from choices (anywhere from 3 to 10)

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

Locally reproducible Leaderboard (v2) scores

1
#946 opened about 2 months ago by ekurtic
New activity in neuralmagic/Meta-Llama-3-8B-Instruct-FP8 3 months ago

Potential problematic behavior of truncation and/or padding?

1
#5 opened 3 months ago by Alchan
New activity in meta-llama/Meta-Llama-3-8B 6 months ago

Add `add_bos_token` and `add_eos_token`
#141 opened 6 months ago by ekurtic

Why are "add_bos_token" and "add_eos_token" missing in tokenizer_config.json ?

1
#140 opened 6 months ago by ekurtic
New activity in HuggingFaceTB/cosmopedia 8 months ago

Concat all subsets?

2
#10 opened 8 months ago by ekurtic
New activity in glaiveai/glaive-coder-7b about 1 year ago

Replication of evals on HumanEval and MBPP
#1 opened about 1 year ago by ekurtic
New activity in mosaicml/mpt-7b-chat about 1 year ago

Fix title in citation info

1
#35 opened about 1 year ago by ekurtic
New activity in reciprocate/llama2-7b-gsm8k about 1 year ago

Finetuning recipe
#1 opened about 1 year ago by ekurtic
New activity in tiiuae/falcon-7b over 1 year ago

Why is alibi: false in the config.json?
#69 opened over 1 year ago by ekurtic