Resources

View closed (13)

Broken audio processing

#42 opened 10 days ago by

souflaeeh

chat template in tokenizer config

#41 opened about 1 month ago by

dmchoi-scale

VLLM error: google/gemma-3n-E4B-it is not a multimodal model None

👀 5

#39 opened 5 months ago by

tatarrecords

How can I finetune mnv5 with my own LLM?

#38 opened 5 months ago by

lsxx

how to let the model transcribe long audio files ?

➕ 4

#37 opened 5 months ago by

StephennFernandes

FP16 version?

#36 opened 5 months ago by

sd17js2

when add new tokens get CUDA error: device-side assert triggered

#34 opened 5 months ago by

mohamed-stifi

Add extra tokens to the tokenizer

#33 opened 5 months ago by

debasisdwivedy

AttributeError: 'HybridCache' object has no attribute 'sliding_window'

#32 opened 5 months ago by

Nasa1423

VRAM usage with transformers

👀 👍 4

#29 opened 6 months ago by

JPSun56

Bigger context length

#28 opened 6 months ago by

olegshulyakov

Why can't I use the vision capability in ollama

#27 opened 6 months ago by

NoobExp

Inside Google Gemma 3n: my PyTorch Profiler insights

#26 opened 6 months ago by

aospan1

How to ask about coordinates of object in prompt?

#25 opened 6 months ago by

ZFTurbo

Prompt and Text Normalizer for Audio Transcription Word Error Rate Calculation

👀 1

#24 opened 6 months ago by

cwoolee

Non-text output?

#21 opened 6 months ago by

sidhusmart

Unexpected error: recompile_limit reached with one_graph=True.

#19 opened 6 months ago by

kkjh0723

Update notebook.ipynb

#17 opened 6 months ago by

sergiopaniego

This model is amazing, but almost too amazing

👍 🔥 7

#16 opened 6 months ago by

nonetrix

[Bug?] google/gemma-3n-E4B-it fails with AttributeError: 'Gemma3nConfig' object has no attribute 'vocab_size'

➕ 3

#15 opened 6 months ago by

EsatKara

Cannot copy out of meta tensor; no data!

#14 opened 6 months ago by

Amit5674

LiteRT launch version?

➕ 7

#13 opened 6 months ago by

Cat7433

Update config.json

#12 opened 6 months ago by

rogerwyf

For some weird reason google ai studio is different from ALL quantizations

#11 opened 6 months ago by

aguspiza

RuntimeError: number of heads in query/key/value should match

#10 opened 6 months ago by

ybathula

how about those multimodal Benchmark like VideoBench ?

➕ 1

#9 opened 6 months ago by

LukeAlan

Vision encoder mobilenetv5_300m_enc is not uploaded to transformers?

➕ 9

#8 opened 6 months ago by

totoro74

tgi fails saying - upgrade tranformers version

#6 opened 6 months ago by

Tollring

Audio example

❤️ 2

#5 opened 6 months ago by

kristaller486