Resources

Update EOS token ids

#46 opened 7 days ago by

nayohan

Update EOS token ids

#45 opened 7 days ago by

nayohan

Update?

#44 opened 16 days ago by

Neman

Batch Inference causes degraded performance

#43 opened 23 days ago by

tanliboy

Sliding window vs. Global Attention

#41 opened 29 days ago by

tanliboy

Problems with sample when using left padding and enable sampling

#40 opened about 1 month ago by

RaccoonOnion

Inquiry on Minimum Configuration and Cost for Running Gemma-2-9B Model Efficiently

#39 opened about 1 month ago by

ltkien2003

Request: DOI

#38 opened about 1 month ago by

XDYeetboy

Update generation_config.json

#32 opened 2 months ago by

runninglsy

Update tokenizer_config.json

#31 opened 2 months ago by

reach-vb

Broadcasting error if "num_return_sequences" in transformers pipeline is greater than 1

#29 opened 2 months ago by

OSalem99

Ran into an issues while I was trying to sample more than one sentence

#27 opened 2 months ago by

joeysss

Hey guys

#25 opened 2 months ago by

zipingl

Why does this model have powerful text generation capabilities for various countries, and the results are very good, most likely in English?

#24 opened 3 months ago by

windkkk

Possible issue with context window

#23 opened 3 months ago by

ieman

Gemma-2 is a huge step up over previous Google OS models - short feedback

#22 opened 3 months ago by

Dampfinchen

Request: DOI

#21 opened 3 months ago by

BEGADE

Gemma 2 - 2B planing

#20 opened 3 months ago by

baohuynhbk14

it looks it do not work as expected , see below

#17 opened 3 months ago by

Sakura77

nonsense response when bsz>1

#16 opened 3 months ago by

jinjieni

Alternative quantizations.

#13 opened 3 months ago by

ZeroWw

not work

#12 opened 3 months ago by

sdyy