google/gemma-7b · Discussions

#98 opened 21 days ago by

crawshaw

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

#97 opened about 1 month ago by

rachiteagles

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

#96 opened about 1 month ago by

LiuWhite

Unable to convert ONNX model to INT4/FP16

#95 opened about 1 month ago by

Avan2000

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

#91 opened about 1 month ago by

UserDAN

Broken Colab Link for Fine Tuning colab

3

#90 opened about 1 month ago by

canyon289

FSDP with Nvidia GPU

#84 opened about 2 months ago by

Iamexperimenting

A new idea to improve training and inference performance

#82 opened 2 months ago by

lijip26313

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

#81 opened 2 months ago by

Pradeep1995

Fine-Tune Gemma with ChatML and Transformer Reinforcement Learning

#80 opened 2 months ago by

Ateeqq

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

#79 opened 2 months ago by

H2dddhxh

Finetuning Genna for Foreign Language

7

#78 opened 2 months ago by

user1357925

Dont download, google scuttled this model

9

#77 opened 2 months ago by

Tom-Neverwinter

Tokenizer inconsistencies in GemmaTokenizerFast

#76 opened 2 months ago by

sanderland

GemmaTokenizerFast and GemmaTokenizer

#74 opened 2 months ago by

PedramR

Shutting down servers during fine-tuning

#73 opened 3 months ago by

yjok0220

How to perform audio transcription and diarization of a wave file

#71 opened 3 months ago by

JDeva

Get Data of each visualisations in a powerbi report

#70 opened 3 months ago by

JDeva

[AUTOMATED] Model Memory Requirements

#67 opened 3 months ago by

model-sizer-bot

Silicon Macs support.

#66 opened 3 months ago by

quantoser

When to release the 'function call' version

#65 opened 3 months ago by

qijizhuahuli

save, loading and inferencing the Gemma model

13

#64 opened 3 months ago by

Iamexperimenting

inquiry for gemma-7b : d_model

#61 opened 3 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

#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

#47 opened 3 months ago by

imone

Very high loss compared to keras

5

#46 opened 3 months ago by

tanimazsin130

Deploy in Sagemaker

#42 opened 3 months ago by

XuanNg

USE GEMMA TO TRANSLATION

#37 opened 3 months ago by

tomsum

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

#35 opened 3 months ago by

erfanzar

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