meta-llama/Llama-4-Scout-17B-16E-Instruct

#62 opened 13 days ago by

ansenang

Less Knowledge Than Llama 3.3 70b?

2

#60 opened 13 days ago by

phil111

No attribute `sliding_window`?

#59 opened 14 days ago by

farzadab

Any luck doing inference in 8xA100?

#57 opened 15 days ago by

taytun

Fine-tuning with BitsAndBytes

#56 opened 15 days ago by

arnavgrg

Update config.json -- important default parameters were left out from the config

#55 opened 15 days ago by

mdabbah-nvidia

VLLM not loading meta-llama/Llama-4-Scout-17B-16E-Instruct

#53 opened 16 days ago by

alokkrsahu

13 B and34 B Pleeease!!! Most people cannot even run this.

4

#52 opened 16 days ago by

UniversalLove333

🍭Llama4 SFT Training Script

2

#47 opened 17 days ago by

study-hjt

Max Output Tokens of Llama-4

#46 opened 17 days ago by

MengboZhou

[Issue report] missing keys in the json files

9

#45 opened 17 days ago by

ShervinGhasemlou

access denied

8

#44 opened 17 days ago by

qulong

FP8 weights

4

#41 opened 18 days ago by

getfit

Update README.md

#40 opened 18 days ago by

mfarre

Update README.md

#39 opened 18 days ago by

mfarre

torch compile compatibility issue

6

#38 opened 18 days ago by

axiomlab

Sagemaker - How to test the image multimodal?

#37 opened 18 days ago by

TheSuperAgent

Access request got denied

6

13

#35 opened 18 days ago by

migtissera

Deploying production ready Llama-4 models on your AWS with vLLM

#34 opened 18 days ago by

agam30

Unethical comparisons with Deepseek replacing chinese languages by thai/vietnamese only

9

#32 opened 19 days ago by

krustik

Request: DOI

#31 opened 19 days ago by

ylx2ai

Couldn't connect

#30 opened 19 days ago by

Wouze

Ridicolous demands for model gate.

9

2

#29 opened 19 days ago by

marksverdhei

🔥🔥🔥中文测评视频

#28 opened 19 days ago by

leo009

Llama 4 - open-source fine-tuning script

#27 opened 19 days ago by

hiyouga

Bug in AutoModel

#26 opened 19 days ago by

random-checkin

pad error

7

8

#25 opened 19 days ago by

bobber

AWQ version?

14

#24 opened 19 days ago by

devops724

Object Detection?

#23 opened 19 days ago by

buckeye17-bah

Thanks zuck

#22 opened 19 days ago by

WyattTheSkid

converstational?

#21 opened 19 days ago by

HassanStar

No one with a consumer grade GPU (< 32 vram) can run the lower L4 model... 😓

10

13

#20 opened 19 days ago by

UniversalLove333

Request denied llama4 - lost access to whole meta-llama repos which I already had access

7

#19 opened 19 days ago by

doaonduty

Thank you!, Is it possible to run this with vLLM or sglang ?