Jue Wang
juewang
AI & ML interests
None yet
Organizations
juewang's activity
Context length?
10
#2 opened 5 months ago
by
turboderp
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6383dc174c48969dcf1b4fce/4N-GY7jVvdk08kp2B8DLh.jpeg)
Missing files?
#1 opened 8 months ago
by
juewang
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1669380535028-61dce5c2af6d5e733e0fb08b.jpeg)
Correct the output dtype of rmsnorm_func
2
#13 opened 11 months ago
by
ag0
how to fine tune peft qlora and SFTTrainer?
11
#2 opened 11 months ago
by
NickyNicky
![](https://cdn-avatars.huggingface.co/v1/production/uploads/641b435ba5f876fe30c5ae0a/OknUuweWxX3IzUZIKZ6CF.png)
Poor performance?
4
#6 opened 12 months ago
by
Fionn
Can you help me fine-tune this with LoRA? (Having an error)
1
#12 opened about 1 year ago
by
AayushShah
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63ff5fc4fe6383d50b29052e/Vk9R5rKqG-Z_ou-55J9x-.jpeg)
What kind of machine would be suitable for this model (in amazon sagemaker)?
5
#7 opened over 1 year ago
by
juusohugs
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1675681614196-629f4d9f5d4565ed65a12f59.jpeg)
Will it be possible to run this on PC with 8 GeForce RTX 3060 with 8 Gb VRAM each?
2
#11 opened about 1 year ago
by
ai2p
Any way to set the "stop, split by" when running the model locally?
4
#26 opened over 1 year ago
by
johnnyracer
VRAM requirements?
4
#8 opened over 1 year ago
by
yahma
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1672330023435-62c6faed53c7156f5bf767ed.png)
Issue with loading model to GPU when using pipeline
2
#5 opened over 1 year ago
by
AlpYu-HubX
work well for some NLP task but failed to find NER from the text!
1
#7 opened over 1 year ago
by
devanghingu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1668071778511-636b7bada3459fe6d06acb91.png)
Is it a wrong prompt?
4
#8 opened over 1 year ago
by
tatyanavidrevich
Feature requests and suggestions for V2
9
#4 opened over 1 year ago
by
zhangce
Template for augmented Q&A
2
#20 opened over 1 year ago
by
vabatista
use accelerate to load model
1
#4 opened over 1 year ago
by
adolf669
This model requires A LOT of resources... But how much? Trying to build a chatbot
9
#3 opened over 1 year ago
by
joanfmendo
Generated Text have issues
10
#22 opened over 1 year ago
by
asifahmed
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1669879497278-6261c62c0568e418d693090a.png)
Is UL2 used?
1
#2 opened over 1 year ago
by
JunnanLi
How to fine tune this openchatkit?
1
#10 opened over 1 year ago
by
Ranjittechie
Question-Answering over documents
3
#19 opened over 1 year ago
by
tmishinev
Confused about bidirectional attention when implementing custom sampling loop
2
#25 opened over 1 year ago
by
ericanthonymitchell
Model behavior during adaptation phase
2
#24 opened over 1 year ago
by
jlli
Fine Tuning // Download Full Weights
2
#23 opened over 1 year ago
by
idop11
PrefixLM finetuning details
1
#21 opened over 1 year ago
by
jlli
How to try it out? I provide WIP
3
#1 opened over 1 year ago
by
billy-ai
What is the fine tuning process of GPT-JT-6B-v1 Copied ? Any Docs available ?
5
#15 opened over 1 year ago
by
MukeshSharma
Effect of UL2 training objective
1
#20 opened over 1 year ago
by
malteos
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5efda656ff69163f6f59e5d2/ru2nfhaNjB9-Ls_vbMq92.jpeg)
Hardware requirements for inference?
6
#9 opened over 1 year ago
by
spartanml
How do you use the bidirectional aspect of the model?
11
#1 opened over 1 year ago
by
BigSalmon
Model license
1
#6 opened over 1 year ago
by
kristaller486
![](https://cdn-avatars.huggingface.co/v1/production/uploads/630920925a5c889aaedc7f33/w00N19M21l2FXe6ZasSYc.jpeg)
Complete noob question - cloned the repository, now what?
3
#17 opened over 1 year ago
by
hansintheair
Will using FP32 be better than using FP16?
1
#18 opened over 1 year ago
by
Zenwill
Generate parameters
2
#5 opened over 1 year ago
by
vonjack
Model sans facts?
2
#10 opened over 1 year ago
by
spartanml
OPT has `max_embedding_size` 2050
1
#3 opened almost 2 years ago
by
TimeRobber