google/gemma-7b · Discussions

gemma-1.1-7b base model?

1

#98 opened 7 days ago by

crawshaw

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

2

#97 opened 19 days ago by

rachiteagles

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

#96 opened 21 days ago by

LiuWhite

Unable to convert ONNX model to INT4/FP16

1

#95 opened 22 days ago by

Avan2000

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

6

#91 opened 24 days ago by

UserDAN

Broken Colab Link for Fine Tuning colab

3

#90 opened 29 days ago by

canyon289

FSDP with Nvidia GPU

1

#84 opened about 1 month ago by

Iamexperimenting

A new idea to improve training and inference performance

#82 opened about 2 months ago by

lijip26313

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

1

#81 opened about 2 months ago by

Pradeep1995

Fine-Tune Gemma with ChatML and Transformer Reinforcement Learning

1

#80 opened about 2 months ago by

Ateeqq

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

#79 opened about 2 months ago by

H2dddhxh

Finetuning Genna for Foreign Language

4

#78 opened about 2 months ago by

user1357925

Dont download, google scuttled this model

9

#77 opened about 2 months ago by

Tom-Neverwinter

Tokenizer inconsistencies in GemmaTokenizerFast

6

#76 opened about 2 months ago by

sanderland

GemmaTokenizerFast and GemmaTokenizer

1

#74 opened 2 months ago by

PedramR

Shutting down servers during fine-tuning

1

#73 opened 2 months ago by

yjok0220

How to perform audio transcription and diarization of a wave file

#71 opened 2 months ago by

JDeva

Get Data of each visualisations in a powerbi report

1

#70 opened 2 months ago by

JDeva

[AUTOMATED] Model Memory Requirements

#67 opened 2 months ago by

model-sizer-bot

Silicon Macs support.

1

#66 opened 2 months ago by

quantoser

When to release the 'function call' version

2

#65 opened 2 months ago by

qijizhuahuli

save, loading and inferencing the Gemma model

13

#64 opened 2 months ago by

Iamexperimenting

inquiry for gemma-7b : d_model

#61 opened 2 months ago by

seongwoon

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

#57 opened 3 months ago by

Alwiin

Activation function

1

#56 opened 3 months ago by

aboros98

quantization won't work on mac silicon devices

3

#55 opened 3 months ago by

sryadava

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

5

#50 opened 3 months ago by

Saicy

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

1

#47 opened 3 months ago by

imone

Very high loss compared to keras

5

#46 opened 3 months ago by

tanimazsin130

Deploy in Sagemaker

6

#42 opened 3 months ago by

XuanNg

USE GEMMA TO TRANSLATION

6

#37 opened 3 months ago by

tomsum

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

2

#35 opened 3 months ago by

erfanzar

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

6

#33 opened 3 months ago by

EarthWorm001

8-bit precision error

12

#32 opened 3 months ago by

saireddy

Factual Accuracy and Reliability Benchmarks

#29 opened 3 months ago by

Taylor658

Why the original GGUF is quite large ?

14

#11 opened 3 months ago by

nopainkiller