Hugging Face's logo

google
/
gemma-2-27b-it

Text Generation
Transformers
Safetensors
gemma2
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
40
New discussion

Gemma enable system prompt

1
#40 opened about 1 month ago by muhammedalkhy

Can't replicate MMLU results for 27b...

1
#39 opened about 1 month ago by cinjonr

What is the difference between "google/gemma-2-27b-it" and "google/gemma-2-27b models"

1
#38 opened about 2 months ago by GeniusMind

Can multiple NVIDIA T4 GPUs be used to deploy Gemma2-27B-IT?

1
#36 opened 3 months ago by armanZhou

Update bitsandbytes examples

1
#33 opened 4 months ago by mdouglas

4 bit and 8 bit bnb quants only generate empty strings or one token repeated endlessly

1
#32 opened 4 months ago by nicorinn-google

gemma-2-27b-it Model Access

1
#30 opened 4 months ago by RAGUWING

4bit-quantized gemma-2-27b-it generates only pad tokens, like '<pad><pad><pad><pad><pad><pad><pad><pad><pad>'.

3
#29 opened 4 months ago by kshinoda

Setting num_return_sequences results in shape mismatch error.

3
#28 opened 5 months ago by Watarungurunnn

BIG UPDATE?

4
#26 opened 5 months ago by GPT007

Does mac book pro m3max 48GB can load gemma2-27b?
#23 opened 5 months ago by omenlyd

__ output

1
#19 opened 5 months ago by BigDeeper

What code was this trained on?

2
#18 opened 5 months ago by grothetr

Exl Quants Please

1
#15 opened 5 months ago by rjmehta

JAX/Flax Implementation

10
#13 opened 5 months ago by lemon-mint

Model repeating information and "spitting out" random characters

3
#12 opened 5 months ago by brazilianslib

RuntimeError: CUDA error: device-side assert triggered

4
#11 opened 5 months ago by Dramilio

Citation URL redirects to Gemma-1

1
#8 opened 5 months ago by yumemio

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

1
#7 opened 5 months ago by Jayakumark