google gemma_pytorch issues

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