Twave's picture

14

Twave

LordTwave

·

AI & ML interests

None yet

Organizations

None yet

LordTwave's activity

New activity in abacusai/Smaug-72B-v0.1 10 months ago

Model is Overaligned, Unusable and gamed for the leaderboard

#17 opened about 1 year ago by

LMSYS Leaderboard? I want human evaluations:)

#27 opened 10 months ago by

New activity in mistralai/Mixtral-8x22B-Instruct-v0.1 10 months ago

Model is paraphrasing text instead of citing it verbatim

#7 opened 11 months ago by

New activity in MaziyarPanahi/calme-2.4-llama3-70b 10 months ago

How did you manage to get your GSM8K a full 1.9 percentage points up from a 15T token trained model?

#7 opened 10 months ago by

New activity in meta-llama/Meta-Llama-3-70B-Instruct 11 months ago

85.44 GSM8K Top on HF - New Record!

#22 opened 11 months ago by

New activity in Contamination/contaminated_proof_7b_v1.0_safetensor 12 months ago

No Baseline (yet?)

#2 opened 12 months ago by

New activity in saltlux/luxia-21.4b-alignment-v1.0 12 months ago

ARC 77.73, HellaSwag 91.88, TOP under 22B - Three new HF Records!

#4 opened about 1 year ago by

91.9 HellaSwag, 79.2 TruthfulQA... And It Sucks. Why do this?

#5 opened 12 months ago by deleted

New activity in yam-peleg/Experiment21-7B 12 months ago

Highest on HF Leaderboard!

#2 opened 12 months ago by

New activity in ibivibiv/alpaca-dragon-72b-v1 about 1 year ago

Small Typo - it's Abacus.AI not Albacus.Ai

#1 opened about 1 year ago by

New activity in CausalLM/34b-beta about 1 year ago

Congrats on the overwhelming MMLU 85.6 score!

#1 opened about 1 year ago by