bigscience/bloom · Discussions

#167 opened almost 2 years ago by

LuvIsBadToTheBone

How can I pretrain the BLOOM?

8

#166 opened almost 2 years ago by

fmf1287

Looking at what makes ChatGPT special...

8

#165 opened almost 2 years ago by

Ioulaum

Donwload size

#163 opened almost 2 years ago by

zz99mz

How can I train Bloom on a specific set of texts?

#162 opened almost 2 years ago by

boomer22

What does it take to self-host Bloom? How much money would that cost?

7

#161 opened almost 2 years ago by

damc

CUDA error while running bloom-accelerate-inference.py | RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasLtMatmul

#160 opened almost 2 years ago by

rsoods

How can I make Bloom stop generating when it should?

#159 opened almost 2 years ago by

lewiswu1209

What is the best way to run Bloom-176B locally at interactive speeds?

#156 opened almost 2 years ago by

aeva

A way to inference and fine-tune BLOOM-176B from Google Colab or locally

#152 opened almost 2 years ago by

borzunov

Problem using bloom-1b3 version

#151 opened almost 2 years ago by

dionatandiego11

BLOOM API inference

#150 opened almost 2 years ago by

Matuesz

Prompt tunning in Bloom for long form text generation

9

#149 opened almost 2 years ago by

info2000

Code generation

#147 opened almost 2 years ago by

celestialme

Commercial Use...

#146 opened almost 2 years ago by

Siyam

Could I generate sample disinformation for research purposes?

#145 opened almost 2 years ago by

Infinity1337

Batching token length

#144 opened almost 2 years ago by

How does hugging face have so many hosted api s running at once?

12

#132 opened about 2 years ago by

Change seed in interference API

#131 opened about 2 years ago by

imwide

What gpu power do you need just to run Bloom, not fine tune?

#130 opened about 2 years ago by

Where can I find a script to fine tune Bloom?

#129 opened about 2 years ago by

Suggest a cloud gpu service to fine tune Bloom.

#128 opened about 2 years ago by

How large is Bloom exactly to load all the checkpoints into gpu ram?

#127 opened about 2 years ago by

Paraphrasing with Bloom

#125 opened about 2 years ago by

Code generation with Bloom

#123 opened about 2 years ago by

SummerSigh

Text summarization with Bloom

13

#122 opened about 2 years ago by

Locally run instance in an RTX 3090 - Performance?

9

#119 opened about 2 years ago by

byeai

Separate training data by country

#117 opened about 2 years ago by

wponhf

Dropout

#116 opened about 2 years ago by

Muennighoff

how can i train bloom

#111 opened about 2 years ago by

s3rgio27

How much GPU memory needed?

#109 opened about 2 years ago by

mazib

how to fine tuning

#105 opened about 2 years ago by

nora1008

Support Korean Language

7

#104 opened about 2 years ago by

MasBakr

Is Few-shots performance optimization possible? (keep initial prompt encoded state)

#101 opened about 2 years ago by

Saiyan

Unable to load Bloom on an EC2 instance

#99 opened about 2 years ago by

viniciusguimaraes

I am doing a project where I need to feed Bloom more than 1000 tokens. is there a paid API where I can have a higher token limit?

#95 opened about 2 years ago by

rexer3000

"Temperature needs to be >0" error

#94 opened about 2 years ago by

sleven

Why does bloom like mattresses soo much?

#90 opened over 2 years ago by

aaronhance

Can Bloom-176B really be evaluated on normal hardware at a rate of 3 minutes per token?

30

#87 opened over 2 years ago by

Philimipp

How to use Bloom InferenceApi with Colab ?

#82 opened over 2 years ago by

Karim-Gamal

Querying Bloom from hugginterface inference api

7

#81 opened over 2 years ago by

sbreit

From Megratron GPT-2 or GPT-3?

#75 opened over 2 years ago by

jmassot

Download and run the model

5

#74 opened over 2 years ago by

HAAR

Inference on TPU-v3-32

#69 opened over 2 years ago by

ybelkada

<s> token

#65 opened over 2 years ago by

Muennighoff

How to use bloom-176B to generate or evaluate on Multi-graphics?

#62 opened over 2 years ago by

xuyifan

Inference on BLOOM 165B is too slow

15

#59 opened over 2 years ago by

mayank-mishra

Hardware Requirements for CPU / GPU Inference

#58 opened over 2 years ago by

jurassicpark

Invalid request from sample code