Jon Durbin's picture

132 6

Jon Durbin PRO

jondurbin

·

https://bmc.link/jondurbin

AI & ML interests

None yet

Organizations

New activity in MiniMaxAI/MiniMax-M2 3 months ago

Ambiguity on interleaved thinking

#38 opened 3 months ago by

New activity in inclusionAI/Ling-1T 3 months ago

Catostrophic Model Failure

#7 opened 3 months ago by

kieraisverybored

New activity in zai-org/GLM-4.6-FP8 4 months ago

Missing MTP?

#1 opened 4 months ago by

New activity in Qwen/Qwen3-235B-A22B-Thinking-2507 6 months ago

Document tool-call parser options in inference engines

#1 opened 6 months ago by

New activity in tngtech/DeepSeek-R1T-Chimera 7 months ago

Chimera not separating reasoning from response

#3 opened 8 months ago by

New activity in jondurbin/bagel-34b-v0.2 over 1 year ago

Update README.md with license information

#5 opened over 1 year ago by

New activity in jondurbin/airoboros-70b-3.3 over 1 year ago

Question

#1 opened over 1 year ago by

New activity in jondurbin/bagel-8b-v1.0 over 1 year ago

Model name

#1 opened almost 2 years ago by

New activity in jondurbin/bagel-jamba-v05 almost 2 years ago

Thank you! Got more details on the fine tuning?

#1 opened almost 2 years ago by

KnutJaegersberg

New activity in jondurbin/bagel-dpo-34b-v0.5 almost 2 years ago

Holy shit this model is amazing!

#1 opened almost 2 years ago by

PartTimePhilosopher

New activity in jondurbin/airoboros-34b-3.2 almost 2 years ago

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

#4 opened almost 2 years ago by

Okay, here's a review. Sorta.

#3 opened almost 2 years ago by

New activity in jondurbin/bagel-34b-v0.4 almost 2 years ago

Hey, got interesting probem here.

#6 opened almost 2 years ago by

New activity in jondurbin/airoboros-34b-3.2 almost 2 years ago

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

#2 opened almost 2 years ago by

New activity in jondurbin/truthy-dpo-v0.1 almost 2 years ago

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

#4 opened almost 2 years ago by

New activity in jondurbin/airoboros-34b-3.2 almost 2 years ago

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

#1 opened almost 2 years ago by

New activity in 01-ai/Yi-34B-200K almost 2 years ago

Weight updates?

#13 opened almost 2 years ago by

New activity in jondurbin/bagel-34b-v0.4 almost 2 years ago

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

#4 opened almost 2 years ago by

When can we anticipate the release of the DPO version?

#3 opened almost 2 years ago by

Difference between v0.2 and v0.4?

#2 opened almost 2 years ago by