google/gemma-7b-it · Discussions

#97 opened 28 days ago by

hk199

Request: DOI

#96 opened about 2 months ago by

GOjira491

Request: DOI

#95 opened 3 months ago by

naman2k23

Rename README.md to !huggingface-cli login

#94 opened 3 months ago by

Thanhtran2209

Rename README.md to !huggingface-cli login

#91 opened 6 months ago by

mandyLO

Bug in logits for BOS token.

9

#90 opened 6 months ago by

Izarel

Inference with RTX 3090 got OOM

#89 opened 7 months ago by

kathylee

gemma 支持agent能力吗？是需要自己微调出来吗

#87 opened 7 months ago by

qijizhuahuli

[AUTOMATED] Model Memory Requirements

#84 opened 7 months ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#83 opened 7 months ago by

model-sizer-bot

Weird Output "emphat emphat emphat"

#82 opened 7 months ago by

bill13031

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 8 months ago by

Subhasisdasgupta

add_special_tokens=False results in poor generation

#80 opened 8 months ago by

DMaksimov

MPS does not support cumsum op with int64 input

#79 opened 8 months ago by

adityapotdar

"No output was generated. Something went wrong."

#78 opened 8 months ago by

JJJJJPSYCHIC

Can several different prompts be handled together?

#77 opened 8 months ago by

WENJINLIU

PermissionError

#75 opened 8 months ago by

Youngdong2

问题2

#74 opened 8 months ago by

wqljwj

Difficulty importing Pipeline - AttributeError: module 'keras._tf_keras.keras' has no attribute 'internal'

8

#71 opened 8 months ago by

mqureshi

How to set a system instruction?

#69 opened 8 months ago by

areumtecnologia

Need info on pre-training and instruction-tuning data

#64 opened 8 months ago by

markding

Import Error when trying to quantize and get any of the gemma models working on my local machine

#63 opened 8 months ago by

Prajwalll

undefined symbol error

#62 opened 8 months ago by

Cgodwin

My vibe-check of Gemma-7B-it. It's pretty good!

#60 opened 8 months ago by

harpreetsahota

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

#59 opened 8 months ago by

mans-0987

Racial discrimination just like in Gemini

4

#57 opened 8 months ago by

justinian336

gemma-7b-it doesn't answer for some questions and returns '/n'

10

#55 opened 8 months ago by

mudogruer

gemma-2b-it model works but gemma-7b-it model generates errors

#51 opened 9 months ago by

saurabhkumar

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

#44 opened 9 months ago by

chenwei1984

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

10

#43 opened 9 months ago by

cooldog

<pad> spam issue

13

#40 opened 9 months ago by

Zewsic

Is it a joke?😅

6

#39 opened 9 months ago by

Horned

Buggy GGUF Output

15

#38 opened 9 months ago by

mattjcly

Alignment Issues

#37 opened 9 months ago by deleted

Bug about number generation?