Hugging Face's logo
Jon Durbin's picture
125 6

Jon Durbin PRO

jondurbin
andytest1's profile picture Minami-su's profile picture pabloce's profile picture
·
https://bmc.link/jondurbin
jon_durbin
jondurbin

AI & ML interests

None yet

Organizations

OpenRouter's profile picture Qwen's profile picture airoboros's profile picture unalignment's profile picture AUGMXNT's profile picture

jondurbin's activity

New activity in HuggingFaceH4/open_llm_leaderboard 4 days ago

airoboros-110b-3.3 disappeared after running?

3
#746 opened 4 days ago by jondurbin
New activity in jondurbin/airoboros-70b-3.3 6 days ago

Question

2
#1 opened 7 days ago by dillfrescott
New activity in jondurbin/bagel-8b-v1.0 22 days ago

Model name

1
#1 opened 23 days ago by Ezk-Trahu-77
New activity in jondurbin/bagel-jamba-v05 about 1 month ago

Thank you! Got more details on the fine tuning?

2
#1 opened about 1 month ago by KnutJaegersberg
New activity in jondurbin/bagel-dpo-34b-v0.5 about 2 months ago

Holy shit this model is amazing!

1
#1 opened about 2 months ago by PartTimePhilosopher
New activity in jondurbin/airoboros-34b-3.2 about 2 months ago

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

2
#4 opened about 2 months ago by aaha

Okay, here's a review. Sorta.

1
#3 opened about 2 months ago by MateoTeo
New activity in jondurbin/bagel-34b-v0.4 about 2 months ago

Hey, got interesting probem here.

2
#6 opened about 2 months ago by MateoTeo
New activity in jondurbin/airoboros-34b-3.2 2 months ago

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

2
#2 opened 2 months ago by SabinStargem
New activity in jondurbin/truthy-dpo-v0.1 2 months ago

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

1
#4 opened 2 months ago by ThiloteE
New activity in jondurbin/airoboros-34b-3.2 2 months ago

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

1
#1 opened 2 months ago by Hoioi
New activity in 01-ai/Yi-34B-200K 2 months ago

Weight updates?

8
#13 opened 2 months ago by brucethemoose
New activity in jondurbin/bagel-34b-v0.4 2 months ago

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

4
#4 opened 3 months ago by Nycoorias
New activity in jondurbin/bagel-34b-v0.4 3 months ago

When can we anticipate the release of the DPO version?

2
#3 opened 3 months ago by HR1777

Difference between v0.2 and v0.4?

1
#2 opened 3 months ago by Light4Bear

Could you please quantify the model?

2
#1 opened 3 months ago by Serpen
New activity in jondurbin/worthless-7b 3 months ago

wtf is this?

1
#1 opened 3 months ago by biship
New activity in jondurbin/bagel-8x7b-v0.2 3 months ago

Chatml format for Bagel

1
#4 opened 4 months ago by adam3245
New activity in jondurbin/mathjson-alpha 3 months ago

Dataset with normal text output?

1
#2 opened 4 months ago by HankN
New activity in unalignment/toxic-dpo-v0.1 4 months ago

Applied reversely for alignment?

4
#2 opened 5 months ago by Yhyu13
New activity in jondurbin/bagel-dpo-34b-v0.2 4 months ago

Weird output with instruction following

1
#4 opened 4 months ago by ndurkee
New activity in jondurbin/truthy-dpo-v0.1 4 months ago

[bot] Conversion to Parquet
#1 opened 5 months ago by parquet-converter

this is really great dataset

1
#2 opened 4 months ago by cloudyu
New activity in internlm/internlm2-base-20b 4 months ago

[fine-tuning] attention_dropout not defined
#2 opened 4 months ago by jondurbin
New activity in jondurbin/bagel-8x7b-v0.2 4 months ago

Benchmarks?

1
#2 opened 4 months ago by rombodawg
New activity in jondurbin/bagel-v0.3 4 months ago

Remove mathinstruct

1
#3 opened 4 months ago by distantquant
New activity in jondurbin/bagel-dpo-8x7b-v0.2 4 months ago

Thank you for your model!

11
#1 opened 4 months ago by rombodawg
New activity in jondurbin/bagel-dpo-34b-v0.2 4 months ago

How may gpu and gpu time used for this training?

2
#3 opened 4 months ago by aisensiy
New activity in jondurbin/gutenberg-dpo-v0.1 4 months ago

Add some aditional metadata
#1 opened 4 months ago by davanstrien
New activity in jondurbin/bagel-v0.3 4 months ago

Empty rows

4
#2 opened 4 months ago by HoangHa
New activity in jondurbin/py-dpo-v0.1 4 months ago

add code language metadata
#1 opened 4 months ago by davanstrien
New activity in jondurbin/bagel-8x7b-v0.2 4 months ago

Update Massed Compute rental. New Coupon Code
#3 opened 4 months ago by nic-mc
New activity in jondurbin/nontoxic-bagel-34b-v0.2 4 months ago

Great Model and Name ;-)

1
#2 opened 4 months ago by DaryoushV
New activity in jondurbin/bagel-8x7b-v0.2 4 months ago

Include Massed Compute VM with Steps
#1 opened 4 months ago by nic-mc
New activity in jondurbin/bagel-34b-v0.2 4 months ago

As this is trained with multiple prompt templates, do you think it can even generalize to ther prompt template?

1
#2 opened 4 months ago by DrNicefellow
New activity in jondurbin/bagel-dpo-34b-v0.2 4 months ago

DPO ruined Bagel's versitility

1
#2 opened 5 months ago by Henk717
New activity in jondurbin/bagel-dpo-34b-v0.2 5 months ago

Nice model!

4
#1 opened 5 months ago by acrastt
New activity in jondurbin/bagel-34b-v0.2 5 months ago

Context Length?

4
#1 opened 5 months ago by brucethemoose
New activity in jondurbin/bagel-dpo-7b-v0.1 5 months ago

Could you please finetune Bagel on Solar 10.7B too?

2
#1 opened 5 months ago by HR1777
New activity in jondurbin/bagel-7b-v0.1 5 months ago

ChatML format

1
#1 opened 5 months ago by andysalerno
New activity in jondurbin/airoboros-l2-70b-3.1.2 5 months ago

Space after [/INST]

7
#2 opened 7 months ago by Satya93
New activity in jondurbin/cinematika-v0.1 6 months ago

[bot] Conversion to Parquet
#1 opened 6 months ago by parquet-converter
New activity in jondurbin/airoboros-l2-c70b-3.1.2 7 months ago

Any positive results so far?

1
#1 opened 7 months ago by Thireus
New activity in jondurbin/airoboros-m-7b-3.1.2 7 months ago

Mistral Model?

1
#1 opened 7 months ago by jjboi8708
New activity in jondurbin/airoboros-l2-70b-gpt4-m2.0 7 months ago

Max Context Token Length

2
#1 opened 7 months ago by lazyDataScientist
New activity in jondurbin/airoboros-3b-3p11 7 months ago

License?

5
#1 opened 7 months ago by acrastt
New activity in TheBloke/Airoboros-L2-13B-3.1.1-AWQ 7 months ago

Update tokenizer_config.json
#1 opened 7 months ago by jondurbin
New activity in TheBloke/Airoboros-L2-13B-3.1.1-GPTQ 7 months ago

Update tokenizer_config.json
#1 opened 7 months ago by jondurbin
New activity in TheBloke/Airoboros-M-7B-3.1.2-GPTQ 7 months ago

Update tokenizer_config.json
#1 opened 7 months ago by jondurbin
New activity in TheBloke/Airoboros-M-7B-3.1.2-AWQ 7 months ago

Update tokenizer_config.json
#1 opened 7 months ago by jondurbin
New activity in TheBloke/Airoboros-c34B-3.1.2-AWQ 7 months ago

Update tokenizer_config.json
#1 opened 7 months ago by jondurbin
New activity in TheBloke/Airoboros-c34B-3.1.2-GPTQ 7 months ago

Update tokenizer_config.json
#1 opened 7 months ago by jondurbin
New activity in TheBloke/Airoboros-L2-70B-3.1.2-AWQ 7 months ago

Update tokenizer_config.json
#1 opened 7 months ago by jondurbin
New activity in TheBloke/Airoboros-L2-70B-3.1.2-GPTQ 7 months ago

Update tokenizer_config.json
#1 opened 7 months ago by jondurbin
New activity in jondurbin/airoboros-l2-70b-3.1.2 7 months ago

Ability to generalise

6
#1 opened 7 months ago by vmajor
New activity in cognitivecomputations/dolphin-2.0-mistral-7b 7 months ago

ChatML prompt format confusion - please reconsider

36
#3 opened 8 months ago by kalomaze
New activity in TheBloke/Airoboros-M-7B-3.1-AWQ 7 months ago

Update tokenizer_config.json
#1 opened 7 months ago by jondurbin
New activity in TheBloke/Airoboros-M-7B-3.1-GPTQ 7 months ago

Update tokenizer_config.json

2
#1 opened 7 months ago by jondurbin
New activity in jondurbin/airoboros-3b-3p0 8 months ago

Remove non-safe model files.
#1 opened 8 months ago by jondurbin
New activity in jondurbin/airoboros-2.2 8 months ago

Notifications from Datasets Server

1
#1 opened 8 months ago by parquet-converter