bigscience/bloom · Discussions

#172 opened 13 days ago by

ankit5678

Learn how to prompt with bloom properly! Create chatbots, with different personalities use bloom as Linux terminal, code generation and more!

#171 opened 14 days ago by

NigelTheMaker

BloomTokenizerFast does not exist

#170 opened 15 days ago by

hiddenchamp

Something between BLOOM-176B and BLOOM-7B1?

#169 opened 15 days ago by

gameveloster

como ejecuto bloom?

#168 opened 15 days ago by

xGaBx

Eats up all RAM + 163GB Swap

#167 opened 18 days ago by

LuvIsBadToTheBone

How can I pretrain the BLOOM?

#166 opened 18 days ago by

fmf1287

Looking at what makes ChatGPT special...

#165 opened 18 days ago by

Ioulaum

Donwload size

#163 opened 23 days ago by

zz99mz

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

#162 opened 28 days ago by

boomer22

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

#161 opened about 1 month ago by

damc

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

#160 opened about 1 month ago by

rsoods

How can I make Bloom stop generating when it should?

#159 opened about 1 month ago by

lewiswu1209

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

#156 opened about 1 month ago by

aeva

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

#152 opened about 2 months ago by

borzunov

Problem using bloom-1b3 version

#151 opened about 2 months ago by

dionatandiego11

BLOOM API inference

#150 opened about 2 months ago by

Matuesz

Prompt tunning in Bloom for long form text generation

8

#149 opened about 2 months ago by

info2000

Code generation

#147 opened about 2 months ago by

celestialme

Commercial Use...

#146 opened about 2 months ago by

Siyam

Could I generate sample disinformation for research purposes?

#145 opened about 2 months ago by

Infinity1337

Batching token length

#144 opened about 2 months ago by

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

12

#132 opened 3 months ago by

Change seed in interference API

#131 opened 3 months ago by

imwide

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

#130 opened 3 months ago by

Where can I find a script to fine tune Bloom?

#129 opened 3 months ago by

Suggest a cloud gpu service to fine tune Bloom.

#128 opened 3 months ago by

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

#127 opened 3 months ago by

Paraphrasing with Bloom

#125 opened 3 months ago by

Code generation with Bloom

#123 opened 3 months ago by

SummerSigh

Text summarization with Bloom

9

#122 opened 3 months ago by

Locally run instance in an RTX 3090 - Performance?

9

#119 opened 4 months ago by

byeai

Separate training data by country

#117 opened 4 months ago by

wponhf

Dropout

#116 opened 4 months ago by

Muennighoff

how can i train bloom

#111 opened 4 months ago by

s3rgio27

How much GPU memory needed?

#109 opened 5 months ago by

mazib

Speed of the hosted inference API for interactive playground

16

#107 opened 5 months ago by

pai4451

how to fine tuning

#105 opened 5 months ago by

nora1008

Support Korean Language

7

#104 opened 5 months ago by

MasBakr

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

#101 opened 5 months ago by

Saiyan

Unable to load Bloom on an EC2 instance

#99 opened 5 months 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 5 months ago by

rexer3000

"Temperature needs to be >0" error

#94 opened 5 months ago by

sleven

Why does bloom like mattresses soo much?

#90 opened 5 months ago by

aaronhance

Getting log probabilities from the Inference API?

12

#89 opened 5 months ago by

Brendan

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

25

#87 opened 5 months ago by

Philimipp

How to use Bloom InferenceApi with Colab ?

#82 opened 6 months ago by

Kareem-Gamal

Querying Bloom from hugginterface inference api

7

#81 opened 6 months ago by

sbreit

From Megratron GPT-2 or GPT-3?