bigscience/bloomz · Discussions

#55 opened 3 months ago by

dsbyprateekg

BLOOMZ answering in a different language

#54 opened 3 months ago by

reemmasoud

Why does the token vocabs are unreadable code?

#53 opened 5 months ago by

ShaneSue

Performance Evaluation

#52 opened 5 months ago by

fatimakqq

base_model_prefix = "transformer"

#51 opened 7 months ago by

Cyrile

Repetitive Output

#50 opened 7 months ago by

fatimakqq

How to get longer outputs?

#49 opened 8 months ago by

Apps

Default padding_side

3

#48 opened 8 months ago by

Cyrile

Are there any special tokens formatted as '<PERSON>', '<LOC>' in the training set or fine-tuning set?

#47 opened 9 months ago by

tingxinli

Is the CausalML model from HuggingFace truly causal?

#46 opened 9 months ago by

Cyrile

bfloat 16 vs float 16

8

#45 opened 9 months ago by

Arkea

Commercial usage

#44 opened 10 months ago by

tingxinli

disable inference API

5

#43 opened 11 months ago by

olivierdehaene

Fine-tuning with LoRA using a dataset with different classification

#42 opened 12 months ago by

karim1104

Removing Stop Token from Decode/Generate

#41 opened about 1 year ago by

JHenzi

Bloomz-3b Refuses to Summarize Text

10

#40 opened about 1 year ago by

Kato-22

What is the maximum input length for Bloomz and MT0?

#39 opened about 1 year ago by

Charm3link

Needed RAM for the full bloomz model?

3

#38 opened about 1 year ago by

luxianos

activate inference widget

#37 opened about 1 year ago by

olivierdehaene

where can we get a bloomz-7b1 finetuned checkpoint

#36 opened about 1 year ago by

yuanzhang0968

Worse performance in Text Generation on Chinese corpus

3

#35 opened about 1 year ago by

WQW

Fix architecture

#34 opened about 1 year ago by

lewtun

Fix architecture class

#33 opened about 1 year ago by

lewtun

Not able to deploy on AWS Sagemaker

#32 opened about 1 year ago by

BahauddinAziz

Is there any company using BLOOMZ as the basis or their service?

6

#31 opened about 1 year ago by

Muhammadreza

Difference between MT0 and BLOOMZ

#30 opened over 1 year ago by

yahma

Will there be a distilled model that fits inside 48GB VRAM (2x 3090)?

#29 opened over 1 year ago by

gameveloster

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

#28 opened over 1 year ago by

borzunov

Unable to edit max_length

#27 opened over 1 year ago by

amuhak

How big is bloomz?

#26 opened over 1 year ago by

hiddenchamp

Can't get it to work

#25 opened over 1 year ago by

hiddenchamp

Train on new un-supported language, i.e. German?

#24 opened over 1 year ago by

kmdanikowski

error on the inference widget

#23 opened over 1 year ago by

clem

generating lists

7

#22 opened over 1 year ago by

i-am-neo

No longer available, why?

11

#21 opened over 1 year ago by

micole66

Weird behavior of BLOOMZ-7b1

8

#20 opened over 1 year ago by

pohunghuang

Zero shot comparison with Instruct-GPT-3 ?

#19 opened over 1 year ago by

nishanthcmesh

Questions on safetensors and text-generation-inference server

17

#18 opened over 1 year ago by

pai4451

Is there a code generation demo?

#17 opened over 1 year ago by

hankcs

tokens

#16 opened over 1 year ago by

mishavee

list of commands

#15 opened over 1 year ago by

mishavee

running and fine tuning

10

#14 opened over 1 year ago by

mishavee

Update README.md

#13 opened over 1 year ago by

Update README.md

#12 opened over 1 year ago by

Update README.md

#11 opened over 1 year ago by

Update README.md

#10 opened over 1 year ago by

Update README.md

#9 opened over 1 year ago by

Nice prompt

#8 opened over 1 year ago by

Add new example

#7 opened over 1 year ago by