Patel
Renu11
AI & ML interests
None yet
Organizations
Renu11's activity
How to increase or decrease the context length?
1
#9 opened 5 months ago
by
CouchCommander
Could not find GemmaForCausalLM neither in <module 'transformers.models.gemma'
5
#44 opened 7 months ago
by
chenwei1984
Layer 13 saes raising "zipfile.BadZipFile: File is not a zip file"
3
#5 opened 18 days ago
by
MrGonao
running it on cpu using pretrained
1
#35 opened 26 days ago
by
himanshuyadav62
Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install accelerate`
2
#19 opened 3 months ago
by
mdeniz1
Issue with loading 4-bit quantized model on Apple M1 pro
2
#45 opened 4 months ago
by
waxsum8
Weird output based on example code
2
#18 opened about 2 months ago
by
mark100
not work
2
#12 opened 3 months ago
by
sdyy
Request: access to gated repo
1
#51 opened about 1 month ago
by
iamamofa
RuntimeError: probability tensor contains either `inf`, `nan` or element < 0
2
#18 opened about 2 months ago
by
lcahill
Running Gemma-2b with Torch 2.0.1?
1
#28 opened about 2 months ago
by
insdaguirre
Getting EnvironmentError
3
#107 opened about 2 months ago
by
Ninad0109
Problem with Lora finetuning, Out of memory
3
#13 opened about 2 months ago
by
zokica
Can multiple NVIDIA T4 GPUs be used to deploy Gemma2-27B-IT?
1
#36 opened about 1 month ago
by
armanZhou
TypeError: arange() received an invalid combination of arguments
4
#12 opened 3 months ago
by
darrenbudiman
system role
5
#15 opened 3 months ago
by
wuriyanto
Model repeating information and "spitting out" random characters
8
#14 opened 3 months ago
by
brazilianslib
add_special_tokens=False results in poor generation
3
#80 opened 6 months ago
by
DMaksimov
nonsense response when bsz>1
5
#16 opened 3 months ago
by
jinjieni
gemma 2b inference Endpoints error
4
#46 opened 6 months ago
by
gawon16
Can several different prompts be handled together?
3
#77 opened 6 months ago
by
WENJINLIU
Gemma-2 is a huge step up over previous Google OS models - short feedback
1
#22 opened 3 months ago
by
Dampfinchen
What code was this trained on?
2
#18 opened 3 months ago
by
grothetr
error of ATen\native\cuda\IndexKernel.cu
6
#14 opened 3 months ago
by
koromatsu
Please mention context size for gemma2 in the model card
2
#19 opened about 2 months ago
by
bionicles
Model repeating information and "spitting out" random characters
3
#12 opened 3 months ago
by
brazilianslib
Is 1.1 trained from the same SFT model as 1.0?
1
#18 opened 5 months ago
by
chujiezheng
Generating multiple responses from the same prompt
2
#50 opened about 2 months ago
by
OfriH
Strange and limited response
3
#15 opened 7 months ago
by
Squeack
Bug about number generation?
5
#30 opened 7 months ago
by
myownskyW7
gemma-2-27b-it Model Access
1
#30 opened 2 months ago
by
RAGUWING
Fails to generate with `inputs_embeds`
2
#18 opened 3 months ago
by
JaronTHU
Gemma2FlashAttention2 missing sliding_window variable
2
#8 opened 3 months ago
by
emozilla
Inference error
8
#20 opened 3 months ago
by
gsasikiran
Error
3
#25 opened 2 months ago
by
ImpactInsights
AttributeError: module 'torch._dynamo' has no attribute 'mark_static_address'
6
#29 opened 2 months ago
by
AsirAsir
A100 can process only 4k tokens
2
#27 opened 3 months ago
by
KubilayCan
base vs instruct model
1
#17 opened 3 months ago
by
saireddy
[FEEDBACK] Notifications
129
#6 opened about 2 years ago
by
victor
ValueError: Transformers does not recognize this architecture.
5
#15 opened 3 months ago
by
mike202303
Support for Flash Attention?
1
#15 opened 3 months ago
by
arnaudstiegler
403 Forbidden: Authorization error
6
#62 opened 4 months ago
by
parkerbotta
loss padding_side
1
#12 opened 6 months ago
by
NickyNicky
Gemma tokenizer issue
1
#37 opened 7 months ago
by
Akshayextreme
ValueError with multi A100 GPUS
1
#28 opened 7 months ago
by
saireddy
8-bit precision error
17
#32 opened 7 months ago
by
saireddy
When to release the 'function call' version
6
#65 opened 7 months ago
by
qijizhuahuli
context window size?
2
#10 opened 6 months ago
by
ichigoberry
What do they mean by maj@1 ?
3
#44 opened 4 months ago
by
joserass
Memory requirements to load the model
1
#61 opened 4 months ago
by
nroshania