google/gemma-7b · Discussions

#113 opened about 2 months ago by

grishi911991

Write a demo on window, can't run end

#112 opened 4 months ago by

xxl4

Request: DOI

#111 opened 5 months ago by

Howl1226

example crushs

#110 opened 6 months ago by

brand17

not appear to have a file named config.json.

#109 opened 7 months ago by

ArcherChiang

Afzal

#108 opened 7 months ago by

advafzal

Getting EnvironmentError

#107 opened 7 months ago by

Ninad0109

need help :(

#106 opened 7 months ago by

yywon

Fine Tuning

#105 opened 8 months ago by

stanford12

Running forever

#103 opened 8 months ago by

guptaru1

Abnormally high loss when fine tunning Gemma-7B

#101 opened 9 months ago by

smart-liu

Gemma 2B model finetuning not working with <s> and </s>

#99 opened 9 months ago by

nicyscaria

gemma-1.1-7b base model?

#98 opened 10 months ago by

crawshaw

Getting permission issue while trying to access the fine tuned model which is present at rachiteagles/cover_letter

#97 opened 10 months ago by

rachiteagles

[DEBUG]transformers 4.38.0 /models/gemma/modeling_gemma.py

#96 opened 10 months ago by

LiuWhite

Unable to convert ONNX model to INT4/FP16

#95 opened 10 months ago by

Avan2000

Weird Performance Issue with Gemma-7b compared to Gemma-2b with Qlora

#91 opened 10 months ago by

UserDAN

Broken Colab Link for Fine Tuning colab

#90 opened 10 months ago by

canyon289

FSDP with Nvidia GPU

#84 opened 11 months ago by

Iamexperimenting

A new idea to improve training and inference performance

#82 opened 11 months ago by

lijip26313

What is the actual context size of google/gemma-7b model

#81 opened 11 months ago by

Pradeep1995

Fine-Tune Gemma with ChatML and Transformer Reinforcement Learning

#80 opened 11 months ago by

Ateeqq

Training Gemma on Domain-Specific Data by Unsupervised Learning t for Specific Instructional Tasks

#79 opened 11 months ago by

H2dddhxh

Finetuning Genna for Foreign Language

10

#78 opened 11 months ago by deleted

Dont download, google scuttled this model

16

#77 opened 11 months ago by

Tom-Neverwinter

Tokenizer inconsistencies in GemmaTokenizerFast

#76 opened 11 months ago by

sanderland

Shutting down servers during fine-tuning

#73 opened 11 months ago by

yjok0220

How to perform audio transcription and diarization of a wave file

#71 opened 11 months ago by

JDeva

Get Data of each visualisations in a powerbi report

#70 opened 11 months ago by

JDeva

[AUTOMATED] Model Memory Requirements

#67 opened 12 months ago by

model-sizer-bot

Silicon Macs support.

#66 opened 12 months ago by

quantoser

When to release the 'function call' version

#65 opened 12 months ago by

qijizhuahuli

save, loading and inferencing the Gemma model

13

#64 opened 12 months ago by

Iamexperimenting

inquiry for gemma-7b : d_model

#61 opened 12 months ago by

seongwoon

[Question]: Gemma Issue with LlamaIndex "query_engine = SQLAutoVectorQueryEngine(sql_tool, vector_tool )"

#57 opened 12 months ago by

Alwiin

Activation function

#56 opened 12 months ago by

aboros98

quantization won't work on mac silicon devices

#55 opened 12 months ago by

sryadava

after sft,model inference problem [probability tensor contains either `inf`, `nan` or element < 0]

5

#50 opened 12 months ago by

Saicy

Consider using an OSI-approved license like Mistral and Phi-2

#47 opened 12 months ago by

imone

Very high loss compared to keras

#46 opened 12 months ago by

tanimazsin130

Deploy in Sagemaker

#42 opened 12 months ago by

XuanNg

USE GEMMA TO TRANSLATION

#37 opened 12 months ago by

tomsum

Gemma Fine-tuning won't work with any other method except SFT

#35 opened 12 months ago by

erfanzar

Very different results with float16. [Actually, gemma-7b-it does not work with float16]

#33 opened 12 months ago by

EarthWorm001

Factual Accuracy and Reliability Benchmarks