Hugging Face's logo
Surya Bhupatiraju's picture
71 2 4

Surya Bhupatiraju

suryabhupa
hfkfabo's profile picture noahtye's profile picture ranjannyu's profile picture
·

AI & ML interests

part of the Gemma Team -- Language models, Reinforcement Learning

Organizations

Google's profile picture

suryabhupa's activity

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

inquiry for gemma-7b : d_model

1
#61 opened 7 months ago by seongwoon
New activity in google/gemma-2-27b-it 3 months ago

Hallucinations, misspellings etc. Something seems broken?

21
#10 opened 3 months ago by sam-paech

tokenizer chat_template has no role system

2
#9 opened 3 months ago by wnma3mz

Citation URL redirects to Gemma-1

1
#8 opened 3 months ago by yumemio

Asking same thing twice or thrice in hugging face chat breaks it , same thing on ollama

1
#7 opened 3 months ago by Jayakumark

transformers load fails?

7
#6 opened 3 months ago by bdambrosio
New activity in google/gemma-2-9b-it 3 months ago

Flash attention 2 is not working

3
#9 opened 3 months ago by nalf3in2
New activity in google/gemma-2b 4 months ago

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

2
#53 opened 6 months ago by ChiYuqi
New activity in google/gemma-2b-it 4 months ago

What do they mean by maj@1 ?

3
#44 opened 5 months ago by joserass
New activity in google/gemma-7b 5 months ago

Fine-Tune a gemma model for question answering

17
#62 opened 7 months ago by Iamexperimenting

save, loading and inferencing the Gemma model

13
#64 opened 7 months ago by Iamexperimenting
New activity in google/gemma-7b-it 5 months ago

Need info on pre-training and instruction-tuning data

3
#64 opened 7 months ago by markding

Inference with RTX 3090 got OOM

3
#89 opened 6 months ago by kathylee
New activity in google/gemma-7b 6 months ago

Weird Performance Issue with Gemma-7b compared to Gemma-2b with Qlora

6
#91 opened 6 months ago by UserDAN
New activity in google/gemma-7b-it 6 months ago

What's the context window for this model?

6
#73 opened 7 months ago by siddheshgunjal
New activity in google/gemma-2b 6 months ago

pretraining Gemma for domain dataset

8
#41 opened 7 months ago by Iamexperimenting

gemma -2b with multi-gpu

3
#44 opened 6 months ago by Iamexperimenting
New activity in google/gemma-7b-it 6 months ago

<pad> spam issue

13
#40 opened 8 months ago by Zewsic
New activity in google/gemma-2b 6 months ago

evaluation loss not calculated during during?

2
#43 opened 6 months ago by Iamexperimenting
New activity in google/gemma-7b 6 months ago

Dont download, google scuttled this model

16
#77 opened 7 months ago by Tom-Neverwinter

Tokenizer inconsistencies in GemmaTokenizerFast

6
#76 opened 7 months ago by sanderland
New activity in google/gemma-7b-it 7 months ago

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

10
#55 opened 7 months ago by mudogruer
commented a paper 7 months ago
New activity in google/gemma-7b-it 7 months ago

Update examples in README to be compatible with soon-to-come ChatWidget

3
#68 opened 7 months ago by Wauplin
New activity in google/gemma-7b 7 months ago

USE GEMMA TO TRANSLATION

6
#37 opened 8 months ago by tomsum
New activity in google/gemma-2b-it 7 months ago

Transformer Pipeline

7
#26 opened 7 months ago by francescoyoubiquo

Max seq length of gemma-2b-it model input

2
#29 opened 7 months ago by zh-jn
New activity in google/gemma-7b-it 7 months ago

Update chat template

3
#48 opened 8 months ago by pcuenq
New activity in google/gemma-7b 7 months ago

Multilingual sft fine-tuning support like Bengali of Gemma-7b

2
#41 opened 8 months ago by sohug

Deploy in Sagemaker

6
#42 opened 8 months ago by XuanNg

Very high loss compared to keras

6
#46 opened 7 months ago by tanimazsin130

Consider using an OSI-approved license like Mistral and Phi-2

1
#47 opened 7 months ago by imone

How to set a system instruction?

1
#53 opened 7 months ago by areumtecnologia

Error when Running Python Code

3
#58 opened 7 months ago by SyntaxError101
New activity in google/gemma-2b-it 7 months ago

GEMMA2B

1
#14 opened 8 months ago by acsankar

How to make gemma run fast on local?

2
#28 opened 7 months ago by dantebytes
New activity in google/gemma-7b-it 7 months ago

how to extract model response from the output of tokenizer

3
#54 opened 8 months ago by mans-0987
New activity in google/gemma-7b 7 months ago

Very different results with float16. [Actually, gemma-7b-it does not work with float16]

6
#33 opened 8 months ago by EarthWorm001
New activity in google/gemma-7b-it 7 months ago

shape is invalid for input

2
#56 opened 7 months ago by Rwbyist

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

5
#59 opened 7 months ago by mans-0987

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

1
#60 opened 7 months ago by harpreetsahota

bin
#67 opened 7 months ago by Abboy123

How to set a system instruction?

2
#69 opened 7 months ago by areumtecnologia

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

10
#43 opened 8 months ago by cooldog

Buggy GGUF Output

15
#38 opened 8 months ago by mattjcly
New activity in google/gemma-2b 7 months ago

Has anyone used this with Chat With RTX Yet

2
#20 opened 8 months ago by TheMildEngineer

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

5
#18 opened 8 months ago by Zhuangl
New activity in google/gemma-7b-it 7 months ago

Bug about number generation?

5
#30 opened 8 months ago by myownskyW7
New activity in google/gemma-7b 7 months ago

gemma-7b not support function call. please add support for it

4
#38 opened 8 months ago by akxor

Update README.md

3
#51 opened 7 months ago by ybelkada
New activity in google/gemma-2b-it 7 months ago

Update README.md

1
#25 opened 7 months ago by eltociear
New activity in google/gemma-7b-it 7 months ago

Racial discrimination just like in Gemini

4
#57 opened 7 months ago by justinian336

Error while training gemma 7-b

5
#49 opened 8 months ago by Mansikalra

2b-it can chat normally, but 7b-it can't

3
#52 opened 8 months ago by Yuanxh

Instruct Training Dataset languages

5
#12 opened 8 months ago by Deniaud
New activity in google/gemma-7b-it 8 months ago

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

2
#51 opened 8 months ago by saurabhkumar

chat format does not match the paper

1
#18 opened 8 months ago by andysalerno

How can I input the sys message for the gemma instruct model?

3
#25 opened 8 months ago by Yingding

Finetuning data format (alpaca or chat)

4
#33 opened 8 months ago by halilergul1
New activity in google/gemma-7b 8 months ago

Weird answer

4
#40 opened 8 months ago by KunAndKun