issues
search
google
/
gemma_pytorch
The official PyTorch implementation of Google's Gemma models
https://ai.google.dev/gemma
Apache License 2.0
5.26k
stars
503
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to solve the 'RESOURCE_EXHAUSTED' error when loading 'gemma2_instruct_2b_en' (the script is from kaggle and runs on colab with TPU)?
#72
nicewang
opened
3 days ago
2
Inconsistent 'query_pre_attn_scalar' Setting Between 9B and 27B Models
#71
kiddj
opened
3 months ago
2
Hope to See the Source Code of Gemma2 Version
#70
thefreeman007
closed
3 months ago
1
Remove unused imports
#69
neurosnap
closed
3 months ago
1
Fix downcasting and upcasting similar to https://github.com/google/ge…
#68
michaelmoynihan
closed
3 months ago
1
Fix downcasting and upcasting
#67
danielhanchen
closed
3 months ago
1
Supporting Gemma V2
#66
michaelmoynihan
closed
3 months ago
1
Update run_xla.py
#65
michaelmoynihan
closed
3 months ago
0
gemma-2b-it-pytorch on tpu v5p
#64
shungcp
closed
3 months ago
1
Modify SentencePiece function calls.
#63
texasmichelle
closed
4 months ago
1
Change return to raise in `get_model_config`.
#62
texasmichelle
closed
4 months ago
1
when to support RecurrentGemma?
#61
Mddct
closed
3 months ago
1
Gemma finetuning formatting
#60
mostafamdy
opened
6 months ago
0
fix missing torch in requirment
#59
Mddct
closed
6 months ago
1
Add CodeGemma and HF pointers
#58
osanseviero
closed
6 months ago
1
early stop when all sequence reach EOS
#57
je1lee
opened
6 months ago
3
Memory saving loading weight for non-quant models
#56
KaneGreen
closed
3 months ago
5
Prepare model for deployment to Private Vertex AI endpoint
#55
BriianPowell
closed
3 months ago
5
Update xla_model_parallel.py
#54
ya0guang
closed
4 months ago
2
Error when run docker/Dockerfile
#53
Cguanqin
opened
6 months ago
2
How to use gemma for multi-round conversations
#52
ranck626
opened
6 months ago
3
How to save memory when loading weights?
#51
KaneGreen
opened
6 months ago
3
Unable to reproduce MATH resulst
#50
wenhuchen
opened
6 months ago
2
fix: raise Exception
#49
leowzz
closed
1 month ago
2
Is it possible to load 7b-it using quantization config
#48
aliasneo1
closed
3 months ago
1
Error when running Gemma inference on GPU
#47
LarryHawkingYoung
closed
1 week ago
3
rm fairescale
#46
Mon-ius
closed
6 months ago
7
I got empty result while using 7b-it model
#45
egbertwong
closed
7 months ago
4
Document the existence of 99 unused tokens in the tokenizer
#44
Qubitium
closed
7 months ago
1
fix(temperature): allow passing 0 or None as the temperature parameter
#43
joselpart
closed
7 months ago
3
Can't disable sampling
#42
joselpart
closed
7 months ago
0
Is max_position_embeddings=8096 neccessary in 2b model?
#41
agiwave
closed
1 week ago
5
Auto-labels 'Gemma' on 'gemma' issues/PRs.
#40
shmishra99
closed
7 months ago
1
Objectivity
#39
o6uoq
closed
7 months ago
0
How to fine-tune Gemma with pytorch?
#38
solitude-alive
closed
7 months ago
2
Gemma fixes - gelu
#37
danielhanchen
closed
7 months ago
4
Torch implementation now same as JAX
#36
thebraingen
closed
7 months ago
1
Implementation now equals JAX
#35
thebraingen
closed
7 months ago
1
Add instructions to download from Hugging Face Hub
#34
osanseviero
closed
7 months ago
1
Inconsistency between PyTorch and JAX implementation
#33
aboros98
closed
7 months ago
2
"--output_len" argument ignored
#32
k-nar
closed
7 months ago
1
not found weight file
#31
Cguanqin
closed
1 week ago
5
is it possible to convert gemma_pytorch to onnx to tflite?
#30
nyadla-sys
closed
1 week ago
4
[Question] Embeddings normalization by sqrt(hidden_size)
#29
Andrei-Aksionov
closed
7 months ago
4
After deplyed google/gemma-7b-it, there always is error response.
#26
ydh10002023
closed
1 week ago
10
Cannot run on v4-16 worker 0 TPU VM: "Failed to get global TPU topology"
#25
markusheimerl
closed
3 weeks ago
6
always loss nan while finetune a few step, wether fp32 or fp16
#24
yongzhuo
closed
7 months ago
1
keras finetuning and inference examples uploaded
#23
r-gheda
closed
7 months ago
2
H
#22
ZainBinTariq7
closed
7 months ago
1
Changed <2B or 7B> to <2b or 7b> in README
#21
r-gheda
closed
7 months ago
0
Next