Jon Durbin's picture

126 6

Jon Durbin PRO

jondurbin

·

https://bmc.link/jondurbin

AI & ML interests

None yet

Organizations

jondurbin's activity

New activity in jondurbin/bagel-34b-v0.2 6 months ago

Update README.md with license information

#5 opened 6 months ago by

New activity in open-llm-leaderboard/open_llm_leaderboard 8 months ago

airoboros-110b-3.3 disappeared after running?

#746 opened 8 months ago by

New activity in jondurbin/airoboros-70b-3.3 8 months ago

Question

#1 opened 8 months ago by

New activity in jondurbin/bagel-8b-v1.0 8 months ago

Model name

#1 opened 8 months ago by

New activity in jondurbin/bagel-jamba-v05 9 months ago

Thank you! Got more details on the fine tuning?

#1 opened 9 months ago by

KnutJaegersberg

New activity in jondurbin/bagel-dpo-34b-v0.5 9 months ago

Holy shit this model is amazing!

#1 opened 9 months ago by

PartTimePhilosopher

New activity in jondurbin/airoboros-34b-3.2 9 months ago

amazing model...can you finetune on a smaller one?

#4 opened 9 months ago by

Okay, here's a review. Sorta.

#3 opened 9 months ago by

New activity in jondurbin/bagel-34b-v0.4 9 months ago

Hey, got interesting probem here.

#6 opened 9 months ago by

New activity in jondurbin/airoboros-34b-3.2 10 months ago

Yi-34b-200k v2, in the cards?

#2 opened 10 months ago by

New activity in jondurbin/truthy-dpo-v0.1 10 months ago

mistral 7b flooding the top of the leaderboard presumably using this dataset. Release truthy-dpo as sft instead.

#4 opened 10 months ago by

New activity in jondurbin/airoboros-34b-3.2 10 months ago

Retain with the latest Yi-34B-200K?

#1 opened 10 months ago by

New activity in 01-ai/Yi-34B-200K 10 months ago

Weight updates?

#13 opened 10 months ago by

New activity in jondurbin/bagel-34b-v0.4 10 months ago

I can’t help but feel like it is worse.

#4 opened 10 months ago by

When can we anticipate the release of the DPO version?

#3 opened 10 months ago by

Difference between v0.2 and v0.4?

#2 opened 10 months ago by

Could you please quantify the model?

#1 opened 10 months ago by

New activity in jondurbin/worthless-7b 11 months ago

wtf is this?

#1 opened 11 months ago by

New activity in jondurbin/bagel-8x7b-v0.2 11 months ago

Chatml format for Bagel

#4 opened 11 months ago by

New activity in jondurbin/mathjson-alpha 11 months ago

Dataset with normal text output?

#2 opened 11 months ago by