have you heard about blender bot 2

  • 9 Replies
  • 545 Views

*

Denis ROBERT

  • Roomba
  • *
  • 12
Re: have you heard about blender bot 2
« Reply #1 on: July 17, 2021, 08:47:06 am »
Quote
In testing, we’ve found that BlenderBot 2.0 outperforms the conversational abilities of the best existing systems.

They all have the best chatbot ;)

*

squarebear

  • Trusty Member
  • *********
  • Terminator
  • *
  • 832
  • It's Hip to be Square
Re: have you heard about blender bot 2
« Reply #2 on: July 17, 2021, 12:30:40 pm »
It certainly isn't the first chatbot to have a long term memory, as they claim.
Feeling Chatty?
www.mitsuku.com

*

chattable

  • Bumblebee
  • **
  • 38
Re: have you heard about blender bot 2
« Reply #3 on: July 17, 2021, 01:17:19 pm »
i wonder if blender bot 2 have short term memory as well?
it would need it for roleplay.
i wonder if they made another ai dungeon with this would it be any good at it?
i wonder how good is it at daydreaming?
« Last Edit: July 17, 2021, 01:47:09 pm by chattable »

*

frankinstien

  • Starship Trooper
  • *******
  • 408
    • Knowledgeable Machines
Re: have you heard about blender bot 2
« Reply #4 on: July 17, 2021, 09:38:58 pm »
"You may talk with our models. The 2.7B can be interacted with on a 16gb P100 GPU or better. The 9.4B parameter model requires at least two 32gb V100 GPUs to interact with."

P100 GPU $4555.00
Double-Precision. Performance 4.7 TeraFLOPS.
Single-Precision. Performance 9.3 TeraFLOPS.
Half-Precision. Performance 18.7 TeraFLOPS.

V100 GPU $12,610.31
FP16 (half) performance 28.26 TFLOPS
FP32 (float) performance 14.13 TFLOPS
FP64 (double) performance 7.066 TFLOPS

Compared to my Vega 56 which cost me, at the time, $425.00.
FP16 (half) performance 21.09 TFLOPS
FP32 (float) performance 10.54 TFLOPS
FP64 (double) performance 659.0 GFLOPS

While the V100 has 34% more computing power, its cost is 35 times greater and the P100 compared to the Vega 56 has 13% less computing power and costs over ten times more! Also, note that double or single precision computation isn't necessary for neural networks. I wish I had bought two of them when they were at bargain prices...
« Last Edit: July 17, 2021, 10:14:40 pm by frankinstien »

*

chattable

  • Bumblebee
  • **
  • 38
Re: have you heard about blender bot 2
« Reply #5 on: July 17, 2021, 10:26:29 pm »
my gpu for my computer is a amd radeon hd.

*

frankinstien

  • Starship Trooper
  • *******
  • 408
    • Knowledgeable Machines
Re: have you heard about blender bot 2
« Reply #6 on: July 17, 2021, 11:04:11 pm »
my gpu for my computer is a amd radeon hd.

I'm referring to my AI server:



The server has two 10 core Intel Xeons for a total of 40 threads and the m2.NVMe SSDs are 3TBs




*

chattable

  • Bumblebee
  • **
  • 38
Re: have you heard about blender bot 2
« Reply #7 on: July 17, 2021, 11:06:23 pm »
oh!

*

MikeB

  • Electric Dreamer
  • ****
  • 107
Re: have you heard about blender bot 2
« Reply #8 on: July 29, 2021, 09:50:13 am »
While the V100 has 34% more computing power, its cost is 35 times greater and the P100 compared to the Vega 56 has 13% less computing power and costs over ten times more

The V100 also has 5120 cores, and the P100 has 3584... some of the later Quadro GPU's have a lot of cores too but are more reasonably priced.

*

MagnusWootton

  • Mechanical Turk
  • *****
  • 175
Re: have you heard about blender bot 2
« Reply #9 on: July 30, 2021, 01:31:49 pm »
my gtx980 has 2048!  very fast beast,  good for raytracing and ai.