Resources

Does Gemma 2 9B Support All Listed Languages on the Gemini 1.5 Page?

#33 opened about 2 months ago by

i18n-site

dtype: float32 in base model vs. dtype: bfloat16 in the instruction fine-tuned model

#32 opened 2 months ago by

tanliboy

Update tokenizer_config.json

#31 opened 2 months ago by

reach-vb

Issues with FSDP and DeepSpeed During Distributed Training for Gemma

#30 opened 2 months ago by

anandhperumal

AttributeError: module 'torch._dynamo' has no attribute 'mark_static_address'

#29 opened 2 months ago by

AsirAsir

CUDA usage is low

#28 opened 2 months ago by

Max545

Fine-tuning Hyperparameters

#27 opened 2 months ago by

tanliboy

Error

#25 opened 2 months ago by

ImpactInsights

RuntimeError: Index put requires the source and destination dtypes match, got BFloat16 for the destination and Float for the source.

#24 opened 2 months ago by

saireddy

Gemma 2's Flash attention 2 implementation is strange...

#23 opened 2 months ago by

GPT007

Request: DOI

#21 opened 3 months ago by

Benjitable

Inference error

#20 opened 3 months ago by

gsasikiran

16 or 32 bit?

#19 opened 3 months ago by

ChrisGoringe

model.generate is throwing AttributeError: 'HybridCache' object has no attribute 'float'

#18 opened 3 months ago by

saireddy

ValueError: Transformers does not recognize this architecture.

#15 opened 3 months ago by

mike202303

Model repeating information and "spitting out" random characters

#14 opened 3 months ago by

brazilianslib

Update README.md

#13 opened 3 months ago by

Criztov

TypeError: arange() received an invalid combination of arguments

#12 opened 3 months ago by

darrenbudiman

Checkpts 9b vs 9b-it storage

#10 opened 3 months ago by

Hemanth-thunder

Aaa

#9 opened 3 months ago by

mohamedzairi

Gemma2FlashAttention2 missing sliding_window variable

#8 opened 3 months ago by

emozilla

Runtime autograd error due to inplace operations

#4 opened 3 months ago by

xianbin