Lavanya KV

#32 opened 6 months ago by

kehkok

New activity in google/gemma-7b-it 13 days ago

How to get a different responce from the model using the same input

#59 opened 7 months ago by

mans-0987

New activity in google/paligemma-3b-pt-224 20 days ago

Pending request

#13 opened 3 months ago by

shiron8bit

New activity in google/codegemma-7b 20 days ago

How can I finetune?

#12 opened 4 months ago by

Mic-k3y

New activity in google/paligemma-3b-pt-896 21 days ago

Italian language?

4

#5 opened 4 months ago by

fcsasdad

New activity in google/codegemma-7b 21 days ago

How to fine-tune?

#11 opened 6 months ago by

Indy97

New activity in google/gemma-2b 27 days ago

Weird token in the tokenizer?

7

#13 opened 7 months ago by

Lambent

New activity in google/gemma-1.1-2b-it 29 days ago

Why removed rope_scaling

#11 opened 6 months ago by

theodotus

New activity in google/gemma-2-2b-it 29 days ago

Request: DOI

#27 opened about 2 months ago by

taloot

New activity in google/gemma-2-9b-it 29 days ago

Context length of the model?

#30 opened 2 months ago by

shipWr3ck

New activity in google/shieldgemma-9b about 1 month ago

Batch Inference

#7 opened about 1 month ago by

dfrank

New activity in google/gemma-7b-it about 1 month ago

MPS does not support cumsum op with int64 input

#79 opened 6 months ago by

adityapotdar

"No output was generated. Something went wrong."

#78 opened 6 months ago by

JJJJJPSYCHIC

New activity in google/shieldgemma-2b about 1 month ago

Batch Inference

#17 opened about 1 month ago by

dfrank

New activity in google/gemma-2b about 1 month ago

Sentiment analysis

#23 opened 7 months ago by

PTsag

New activity in google/gemma-7b-it about 1 month ago

Instrct version models keep missing the first few letters of the answer

10

#43 opened 7 months ago by

cooldog

Buggy GGUF Output

15

#38 opened 7 months ago by

mattjcly

New activity in google/gemma-2-2b-it about 1 month ago

Cannot access Gemma even after approval

#30 opened about 1 month ago by

Daaku-C5

New activity in google/gemma-7b-it about 1 month ago

ValueError: Trying to set a tensor of shape torch.Size([4096, 3072]) in "weight" (which has shape torch.Size([6291456, 1])), this look incorrect.

#81 opened 6 months ago by

Subhasisdasgupta

add_special_tokens=False results in poor generation

#80 opened 6 months ago by

DMaksimov

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

Request: DOI

#21 opened 3 months ago by

BEGADE

New activity in google/gemma-2b about 2 months ago

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 7 months ago by

brando

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

#18 opened 7 months ago by

Zhuangl

New activity in google/gemma-7b-it about 2 months ago

Could not find GemmaForCausalLM neither in <module 'transformers.models.gemma'

6

#36 opened 7 months ago by

chenwei1984

New activity in google/paligemma-3b-ft-science-qa-448-jax about 2 months ago

how to load this .npz model

#3 opened 3 months ago by

bsmani

New activity in google/paligemma-3b-ft-ai2d-224-jax about 2 months ago

how to load this .npz model

#3 opened 3 months ago by

bsmani

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

Request: DOI

#21 opened 3 months ago by

Benjitable

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

Feature extraction suitability?

#52 opened 5 months ago by

ivoras

New activity in google/gemma-7b 2 months ago

Gemma 2B model finetuning not working with <s> and </s>

#99 opened 4 months ago by

nicyscaria

[Question]: Gemma Issue with LlamaIndex "query_engine = SQLAutoVectorQueryEngine(sql_tool, vector_tool )"

#57 opened 7 months ago by

Alwiin

New activity in google/gemma-1.1-7b-it 2 months ago

Do I need to apply_chat_template before Supervised Fine-tuning Gemma-1.1-7b-it?

#19 opened 5 months ago by

Syax19

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

Running finetuned inference on CPU - accelerate ImportError

#54 opened 5 months ago by

saikrishna6491

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

Gemma 2 - 2B planing

4

#20 opened 3 months ago by

baohuynhbk14

New activity in google/gemma-7b 3 months ago

Very high loss compared to keras

6

#46 opened 7 months ago by

tanimazsin130

New activity in google/gemma-7b 4 months ago

Shutting down servers during fine-tuning

#73 opened 6 months ago by

yjok0220

New activity in google/gemma-1.1-7b-it 4 months ago

What is the max sequence length that model can compute if I use flash attention?