Jon Durbin PRO
jondurbin
AI & ML interests
None yet
Organizations
jondurbin's activity
Update README.md with license information
#5 opened 27 days ago
by
Chen-01AI
airoboros-110b-3.3 disappeared after running?
3
#746 opened 2 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Question
2
#1 opened 2 months ago
by
dillfrescott
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6215ce9abfcb3893344dd0a2/ez4OeVTMOpRBCZNjIufoF.jpeg)
Model name
1
#1 opened 3 months ago
by
Ezk-Trahu-77
Thank you! Got more details on the fine tuning?
2
#1 opened 3 months ago
by
KnutJaegersberg
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1669551186189-63732ebbbd81fae2b3aaf3fb.jpeg)
Holy shit this model is amazing!
1
#1 opened 4 months ago
by
PartTimePhilosopher
![](https://cdn-avatars.huggingface.co/v1/production/uploads/635e6d1f928a42bc95c891f5/2Gy86xI8FVoTVwGR5jsKB.png)
amazing model...can you finetune on a smaller one?
2
#4 opened 4 months ago
by
aaha
Okay, here's a review. Sorta.
1
#3 opened 4 months ago
by
MateoTeo
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/HAUQsebGxOFzt6Pi1_yRV.png)
Hey, got interesting probem here.
2
#6 opened 4 months ago
by
MateoTeo
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/HAUQsebGxOFzt6Pi1_yRV.png)
Yi-34b-200k v2, in the cards?
2
#2 opened 5 months ago
by
SabinStargem
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/TKk0SYTJxvCYG3tZPpTQt.jpeg)
Retain with the latest Yi-34B-200K?
1
#1 opened 5 months ago
by
Hoioi
Weight updates?
8
#13 opened 5 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
I can’t help but feel like it is worse.
4
#4 opened 5 months ago
by
Nycoorias
When can we anticipate the release of the DPO version?
2
#3 opened 5 months ago
by
HR1777
Difference between v0.2 and v0.4?
1
#2 opened 5 months ago
by
Light4Bear
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1666277867924-noauth.png)
Could you please quantify the model?
2
#1 opened 5 months ago
by
Serpen
wtf is this?
1
#1 opened 6 months ago
by
biship
Chatml format for Bagel
1
#4 opened 6 months ago
by
adam3245
Dataset with normal text output?
1
#2 opened 6 months ago
by
HankN
Applied reversely for alignment?
4
#2 opened 7 months ago
by
Yhyu13
Weird output with instruction following
1
#4 opened 6 months ago
by
ndurkee
[bot] Conversion to Parquet
#1 opened 7 months ago
by
parquet-converter
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1658495802629-61f02cf649ea1fb7363729dc.png)
this is really great dataset
1
#2 opened 6 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
[fine-tuning] attention_dropout not defined
#2 opened 6 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Benchmarks?
1
#2 opened 7 months ago
by
rombodawg
![](https://cdn-avatars.huggingface.co/v1/production/uploads/642cc1c253e76b4c2286c58e/fGtQ_QeTjUgBhIT89dpUt.jpeg)
Remove mathinstruct
1
#3 opened 6 months ago
by
distantquant
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/3b0gTyU1-iBzQ-Epi0RwX.png)
Thank you for your model!
11
#1 opened 6 months ago
by
rombodawg
![](https://cdn-avatars.huggingface.co/v1/production/uploads/642cc1c253e76b4c2286c58e/fGtQ_QeTjUgBhIT89dpUt.jpeg)
How may gpu and gpu time used for this training?
2
#3 opened 6 months ago
by
aisensiy
Add some aditional metadata
#1 opened 6 months ago
by
davanstrien
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1627505688463-60107b385ac3e86b3ea4fc34.jpeg)
Empty rows
4
#2 opened 6 months ago
by
HoangHa
![](https://cdn-avatars.huggingface.co/v1/production/uploads/630a5ef0e81e1dea2cedcec0/ATtyCvYoX4z7uxsm2sJU2.png)
add code language metadata
#1 opened 6 months ago
by
davanstrien
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1627505688463-60107b385ac3e86b3ea4fc34.jpeg)
Update Massed Compute rental. New Coupon Code
#3 opened 7 months ago
by
nic-mc
Great Model and Name ;-)
1
#2 opened 7 months ago
by
DaryoushV
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65189dea66e78720a750f9a9/D-oSwjCcfQOzZG2w_SvEM.png)
Include Massed Compute VM with Steps
#1 opened 7 months ago
by
nic-mc
DPO ruined Bagel's versitility
1
#2 opened 7 months ago
by
Henk717
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1640356718818-61c47e9c71a107e9d80e33e3.jpeg)
Nice model!
4
#1 opened 7 months ago
by
acrastt
Context Length?
4
#1 opened 7 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Could you please finetune Bagel on Solar 10.7B too?
2
#1 opened 7 months ago
by
HR1777
ChatML format
1
#1 opened 7 months ago
by
andysalerno
Space after [/INST]
7
#2 opened 9 months ago
by
Satya93
[bot] Conversion to Parquet
#1 opened 8 months ago
by
parquet-converter
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1658495802629-61f02cf649ea1fb7363729dc.png)
Any positive results so far?
1
#1 opened 9 months ago
by
Thireus
Mistral Model?
1
#1 opened 9 months ago
by
jjboi8708
Max Context Token Length
2
#1 opened 9 months ago
by
lazyDataScientist
![](https://cdn-avatars.huggingface.co/v1/production/uploads/633a39ec8f27255b6b571101/7J_BcRm7ua0WZNIGwEzlo.png)
License?
5
#1 opened 9 months ago
by
acrastt
Update tokenizer_config.json
#1 opened 9 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Update tokenizer_config.json
#1 opened 9 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Update tokenizer_config.json
#1 opened 9 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Update tokenizer_config.json
#1 opened 9 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Update tokenizer_config.json
#1 opened 9 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Update tokenizer_config.json
#1 opened 9 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Update tokenizer_config.json
#1 opened 9 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Update tokenizer_config.json
#1 opened 9 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Ability to generalise
6
#1 opened 9 months ago
by
vmajor
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63992e59afe0d224cf2b6bf1/q2JeqTcIb5j6fUg1SWGzL.jpeg)
ChatML prompt format confusion - please reconsider
36
#3 opened 10 months ago
by
kalomaze
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6491e00e057b0928b3e07b75/j31tFTZuAqfE5gYfZqSdI.jpeg)
Update tokenizer_config.json
#1 opened 9 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Update tokenizer_config.json
2
#1 opened 9 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)
Remove non-safe model files.
#1 opened 10 months ago
by
jondurbin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6453dafca647b92069ac541a/QkUleoJtHHdTkqtW54QIG.jpeg)