Hugging Face's logo
Zoran's picture
27

Zoran

zokica
iproskurina's profile picture
·

AI & ML interests

None yet

Organizations

None yet

zokica's activity

New activity in google/gemma-2-9b 3 months ago

Gemma 2's Flash attention 2 implementation is strange...

61
#23 opened 4 months ago by GPT007
New activity in google/gemma-2-2b 3 months ago

Problem with Lora finetuning, Out of memory

3
#13 opened 3 months ago by zokica
New activity in unsloth/gemma-2-2b-bnb-4bit 3 months ago

OOM when finetuning with lora.

5
#1 opened 3 months ago by zokica
New activity in unsloth/gemma-2-9b-bnb-4bit 3 months ago

Peft out of memory
#2 opened 3 months ago by zokica
New activity in google/gemma-2-9b 4 months ago

Model repeating information and "spitting out" random characters

8
#14 opened 4 months ago by brazilianslib

Gemma2FlashAttention2 missing sliding_window variable

2
#8 opened 5 months ago by emozilla
New activity in upstage/SOLAR-10.7B-Instruct-v1.0 4 months ago

Why batch size>1 does not increase model speed
#41 opened 4 months ago by zokica
New activity in EleutherAI/pile-t5-large 4 months ago

why UMT5

6
#1 opened 7 months ago by pszemraj
New activity in microsoft/phi-1_5 7 months ago

Something broken on last update

7
#85 opened 7 months ago by Nayjest
New activity in rhysjones/phi-2-orange 7 months ago

Can't get it to generate the EOS token and beam search is not supported

2
#3 opened 9 months ago by miguelcarv
New activity in microsoft/phi-2 7 months ago

How to fine-tune this? + Training code

43
#19 opened 11 months ago by cekal
New activity in rhysjones/phi-2-orange-v2 7 months ago

Added token

1
#5 opened 7 months ago by zokica
New activity in microsoft/phi-2 7 months ago

Generation after finetuning does not ends at EOS token

1
#123 opened 7 months ago by zokica
New activity in microsoft/phi-1_5 about 1 year ago

Attention mask for generation function in the future?

21
#7 opened about 1 year ago by rchan26
New activity in mosaicml/mpt-30b-chat over 1 year ago

The model is extremelly slow in 4bit, is my code for loading ok?

#7 opened over 1 year ago by zokica
New activity in TheBloke/guanaco-33B-GPTQ over 1 year ago

guanaco-65b

6
#1 opened over 1 year ago by bodaay
New activity in mosaicml/mpt-7b over 1 year ago

Speed on CPU

13
#8 opened over 1 year ago by zokica

Will you make a 3B model as well?

4
#7 opened over 1 year ago by zokica
New activity in Sosaka/Alpaca-native-4bit-ggml over 1 year ago

How do you run this?

3
#2 opened over 1 year ago by zokica
New activity in openai-community/roberta-base-openai-detector over 1 year ago

How to run this?

3
#13 opened over 1 year ago by zokica