hai
cloudyu
AI & ML interests
Personal contributor
m2 ultra 192G
QQ 206 887 187
Organizations
cloudyu's activity
good model
1
#1 opened 13 days ago
by
gopi87
when tryy the code, AttributeError: type object 'QuantizedLinear' has no attribute 'quantize_module' report
4
#1 opened about 1 month ago
by
cloudyu
"status" is "FINISHED", but I cannot find the result of my model
1
#694 opened about 1 month ago
by
cloudyu
output is not correct.
1
#7 opened about 1 month ago
by
flymonk
how to run WizardLM-2-8x22B.Q4_K_S.gguf.part2of2 and part1?
3
#1 opened about 1 month ago
by
cloudyu
can you plesse share how to make this version?
3
#3 opened about 1 month ago
by
cloudyu
How much RAM does it need to run on Mac m1?
5
#2 opened about 2 months ago
by
davideuler
MMLU is only 25.64, anything wrong?
5
#8 opened about 2 months ago
by
cloudyu
VRAM Estimates
5
#3 opened 3 months ago
by
ernestr
From your work, I find a new way to do model ensemble
1
#14 opened about 2 months ago
by
xxx1
Hardware requirement
2
#5 opened 2 months ago
by
Dtree07
Adding Evaluation Results
1
#4 opened 2 months ago
by
ac-automata
4x version
1
#15 opened 2 months ago
by
ehartford
Very interesting
1
#1 opened 3 months ago
by
ehartford
Thank you for your continued contribution to Chinese-language community|感谢你对中文社区的持续贡献
1
#1 opened 3 months ago
by
sdakfjlkfasf
Why did you take down gemma-7b-it-dpo-v1
1
#2 opened 3 months ago
by
rombodawg
how to run this model?
3
#1 opened 3 months ago
by
cloudyu
Adding Evaluation Results
1
#1 opened 3 months ago
by
leaderboard-pr-bot
这个是基于中文的微调吗 效果这么好
1
#2 opened 4 months ago
by
xuan0126
Train after merging?
2
#1 opened 3 months ago
by
adi-kmt
how to run this model
#2 opened 3 months ago
by
cloudyu
Upload tokenizer.model
1
#1 opened 4 months ago
by
Nexesenex
Upload tokenizer.model
#2 opened 4 months ago
by
Nexesenex
how to dequantised from q5 to f16?
#7 opened 4 months ago
by
cloudyu
Update README.md
#2 opened 4 months ago
by
cloudyu
Update README.md
#1 opened 4 months ago
by
cloudyu
Can you make a 2.4bpw exl2 quantisation for this model?
4
#1 opened 4 months ago
by
xldistance
How did you train the gating?
10
#6 opened 4 months ago
by
osanseviero
Unable to access cloudyu/Pluto_24B_DPO_400
1
#1 opened 4 months ago
by
umarbutler
this is really great dataset
1
#2 opened 4 months ago
by
cloudyu
Could you share the training script?
1
#1 opened 4 months ago
by
andysalerno
Announcement: Flagging merged models with incorrect metadata
78
#510 opened 5 months ago
by
clefourrier
congrat!new SOTA!
4
#1 opened 4 months ago
by
cloudyu
How many GPU memories that the MoE module needs?
2
#8 opened 4 months ago
by
Jazzlee
The function_calling and translation abilities are weaker than Mixtral 8x7b
1
#11 opened 4 months ago
by
bingw5
Multi-langua?
1
#7 opened 4 months ago
by
oFDz
8.0bpw-h8-exl2 quant of this model
6
#1 opened 4 months ago
by
Light4Bear
The difference of prompt template between base models
3
#8 opened 4 months ago
by
Cartinoe5930
Do you need fine-tune after merging?
3
#5 opened 4 months ago
by
tanganke
Can VLLM be used for inference acceleration?
2
#2 opened 4 months ago
by
obtion
Vram
2
#7 opened 4 months ago
by
DKRacingFan
source code and paper?
8
#6 opened 5 months ago
by
josephykwang
How does the MoE work?
3
#5 opened 5 months ago
by
PacmanIncarnate
Should not be called mixtral, the models made into the moe are yi based
9
#2 opened 5 months ago
by
teknium
Problem with tokenizer
1
#4 opened 5 months ago
by
ipechman
One or two models during inference?
3
#3 opened 5 months ago
by
Venkman42
Can You Share Your Config
3
#2 opened 5 months ago
by
Weyaxi
How to merge models into moe?
2
#1 opened 5 months ago
by
Yhyu13
Why is not working? Please advice as I'm a complete beginner
2
#14 opened 5 months ago
by
ciclide80
Switches from English prompt to Chinese response
6
#6 opened 8 months ago
by
Dove5632
how to run this model?
1
#2 opened 9 months ago
by
cloudyu