google/gemma-2b · Discussions

#67 opened 8 days ago by

robgarct

gemma 2b

#65 opened 14 days ago by

powei59

Any one who use the script in the Model Card for inference purpose?

#64 opened 18 days ago by

disper84

huhuhuhus

#63 opened 22 days ago by

huhuhuhus

403 Forbidden: Authorization error

6

#62 opened 25 days ago by

parkerbotta

Memory requirements to load the model

#61 opened about 2 months ago by

nroshania

Following blog for fine tuning gemma-2b doesn't yield same results

11

#60 opened about 2 months ago by

chongdashu

[AUTOMATED] Model Memory Requirements

#59 opened 2 months ago by

[AUTOMATED] Model Memory Requirements

#58 opened 2 months ago by

[AUTOMATED] Model Memory Requirements

#57 opened 2 months ago by

[AUTOMATED] Model Memory Requirements

#56 opened 2 months ago by

[AUTOMATED] Model Memory Requirements

#55 opened 2 months ago by

Running finetuned inference on CPU - accelerate ImportError

#54 opened 2 months ago by

saikrishna6491

Unable to reproduce the score of gemma_2b at pass@1 in humaneval.

#53 opened 3 months ago by

ChiYuqi

Feature extraction suitability?

#52 opened 3 months ago by

ivoras

Update README.md

#51 opened 3 months ago by

raj729

gemma 2b inference Endpoints error

3

#46 opened 3 months ago by

gawon16

gemma -2b with multi-gpu

3

#44 opened 3 months ago by

Iamexperimenting

pretraining Gemma for domain dataset

8

#41 opened 4 months ago by

Iamexperimenting

[AUTOMATED] Model Memory Requirements

#40 opened 4 months ago by

Gemma tokenizer issue

#37 opened 4 months ago by

Akshayextreme

Question about their name.. why it is 2b???

#36 opened 4 months ago by

sh0416

[AUTOMATED] Model Memory Requirements

#35 opened 4 months ago by

[AUTOMATED] Model Memory Requirements

#34 opened 4 months ago by

What is the context size for Gemma? I get error when asking for it in the config file e.g., AttributeError("'GemmaConfig' object has no attribute 'context_length'")

#32 opened 4 months ago by

brando

torch import required in examples

#31 opened 4 months ago by

shamikbose89

ImportError: Using `bitsandbytes` 8-bit quantization requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes

13

#29 opened 4 months ago by

WQW

torch.cuda.OutOfMemoryError

3

#26 opened 4 months ago by

shiwanglai

GPU utlisation high on Gemma-2b-it

#24 opened 4 months ago by

sharad07

Sentiment analysis

#23 opened 4 months ago by

PTsag

Note on adding new elements to the vocabulary

#21 opened 4 months ago by

johnhew

Has anyone used this with Chat With RTX Yet

#20 opened 4 months ago by

TheMildEngineer

Update README.md

#19 opened 4 months ago by

shamikbose89

Fail to reproduce results on server benchmark by using lm-evaluation-harness

4

#18 opened 4 months ago by

Zhuangl

Strange and limited response