google
/

gemma-1.1-7b-it

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (12)

[AUTOMATED] Model Memory Requirements

#21 opened 7 months ago by

model-sizer-bot

What is the max sequence length that model can compute if I use flash attention?

#20 opened 8 months ago by

Do I need to apply_chat_template before Supervised Fine-tuning Gemma-1.1-7b-it?

#19 opened 8 months ago by

Is 1.1 trained from the same SFT model as 1.0?

#18 opened 8 months ago by

finetunr error. "triu_tril_cuda_template" not implemented for 'BFloat16'

#17 opened 8 months ago by

Update README.md

#16 opened 9 months ago by

TemplateError: System role not supported

#15 opened 9 months ago by

Consider adding <start_of_context> and <stop_of_context> or similar special tokens for context ingestion.

#13 opened 9 months ago by

loss padding_side

#12 opened 9 months ago by

Why is this completely broken?

#11 opened 9 months ago by

Number of parameters

#9 opened 9 months ago by