Hugging Face's logo
Jue Wang's picture
37 7

Jue Wang

juewang
21world's profile picture zayjean's profile picture thomwolf's profile picture
·
https://juewang.me/about/
JueWANG26088228
LorrinWWW

AI & ML interests

None yet

Organizations

Together's profile picture lawinstruct's profile picture DS3Lab's profile picture Striping's profile picture

juewang's activity

New activity in codellama/CodeLlama-70b-Instruct-hf 3 months ago

Context length?

10
#2 opened 3 months ago by turboderp
New activity in EleutherAI/neox-ckpt-pythia-12b-v1 6 months ago

Missing files?
#1 opened 6 months ago by juewang
New activity in togethercomputer/LLaMA-2-7B-32K 9 months ago

Correct the output dtype of rmsnorm_func

2
#13 opened 9 months ago by ag0

how to fine tune peft qlora and SFTTrainer?

11
#2 opened 9 months ago by NickyNicky
New activity in togethercomputer/RedPajama-INCITE-7B-Instruct 10 months ago

Poor performance?

4
#6 opened 10 months ago by Fionn
New activity in togethercomputer/GPT-NeoXT-Chat-Base-20B about 1 year ago

Can you help me fine-tune this with LoRA? (Having an error)

1
#12 opened about 1 year ago by AayushShah

What kind of machine would be suitable for this model (in amazon sagemaker)?

5
#7 opened about 1 year ago by juusohugs

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
New activity in togethercomputer/GPT-JT-6B-v1 about 1 year ago

Any way to set the "stop, split by" when running the model locally?

4
#26 opened about 1 year ago by johnnyracer
New activity in togethercomputer/OpenChatKit about 1 year ago

VRAM requirements?

4
#8 opened about 1 year ago by yahma
New activity in togethercomputer/GPT-NeoXT-Chat-Base-20B about 1 year ago

Issue with loading model to GPU when using pipeline

2
#5 opened about 1 year ago by AlpYu-HubX
New activity in togethercomputer/OpenChatKit about 1 year ago

work well for some NLP task but failed to find NER from the text!

1
#7 opened about 1 year ago by devanghingu
New activity in togethercomputer/GPT-NeoXT-Chat-Base-20B about 1 year ago

Is it a wrong prompt?

4
#8 opened about 1 year ago by tatyanavidrevich
New activity in togethercomputer/GPT-JT-6B-v1 about 1 year ago

Feature requests and suggestions for V2

9
#4 opened over 1 year ago by zhangce
New activity in togethercomputer/OpenChatKit about 1 year ago

Template for augmented Q&A

2
#20 opened about 1 year ago by vabatista
New activity in togethercomputer/GPT-NeoXT-Chat-Base-20B about 1 year ago

use accelerate to load model

1
#4 opened about 1 year ago by adolf669

This model requires A LOT of resources... But how much? Trying to build a chatbot

9
#3 opened about 1 year ago by joanfmendo
New activity in togethercomputer/GPT-JT-6B-v1 about 1 year ago

Generated Text have issues

10
#22 opened about 1 year ago by asifahmed
New activity in togethercomputer/GPT-NeoXT-Chat-Base-20B about 1 year ago

Is UL2 used?

1
#2 opened about 1 year ago by JunnanLi
New activity in togethercomputer/OpenChatKit about 1 year ago

How to fine tune this openchatkit?

1
#10 opened about 1 year ago by Ranjittechie
New activity in togethercomputer/GPT-JT-6B-v1 about 1 year ago

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 about 1 year ago by ericanthonymitchell

Model behavior during adaptation phase

2
#24 opened about 1 year ago by jlli

Fine Tuning // Download Full Weights

2
#23 opened about 1 year ago by idop11

PrefixLM finetuning details

1
#21 opened about 1 year ago by jlli
New activity in togethercomputer/GPT-JT about 1 year ago

How to try it out? I provide WIP

3
#1 opened over 1 year ago by billy-ai
New activity in togethercomputer/GPT-JT-6B-v1 about 1 year ago

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 about 1 year ago by malteos

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

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
New activity in togethercomputer/GPT-JT over 1 year ago

Generate parameters

2
#5 opened over 1 year ago by vonjack
New activity in togethercomputer/GPT-JT-6B-v1 over 1 year ago

Model sans facts?

2
#10 opened over 1 year ago by spartanml
New activity in facebook/opt-66b almost 2 years ago

OPT has `max_embedding_size` 2050

1
#3 opened almost 2 years ago by TimeRobber