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

#71 opened 8 days ago by

brando

Gated Repo Permission Still Pending for Llama-4

#70 opened 8 days ago by

bryka

Gated Repo Permission Still Pending for Llama-4

#69 opened 10 days ago by

brando

Gated Repo Permission Still Pending for Llama-4

4

#68 opened 11 days ago by

bitmman-nch

World's Largest Dataset

#67 opened 17 days ago by

UJJAWAL-TYAGI

Is it possible to reduce the number of llama4 expert models to use less memory?

#65 opened 19 days ago by

gukui

Does LLama4 have chunked attention in generation phase ?

#64 opened 21 days ago by

vanshils

The "force_words_ids" does not seem to be available on llama4

#63 opened 23 days ago by

nlp-g

Access Rejected

#62 opened 25 days ago by

ansenang

Less Knowledge Than Llama 3.3 70b?

#60 opened 25 days ago by

phil111

No attribute `sliding_window`?

#59 opened 26 days ago by

farzadab

Any luck doing inference in 8xA100?

#57 opened 27 days ago by

taytun

Fine-tuning with BitsAndBytes

#56 opened 27 days ago by

arnavgrg

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

#55 opened 27 days ago by

mdabbah-nvidia

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

#53 opened 28 days ago by

alokkrsahu

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

4

#52 opened 28 days ago by

UniversalLove333

🍭Llama4 SFT Training Script

#47 opened 29 days ago by

study-hjt

Max Output Tokens of Llama-4

#46 opened 29 days ago by

MengboZhou

[Issue report] missing keys in the json files

9

#45 opened 29 days ago by

ShervinGhasemlou

access denied

8

#44 opened 29 days ago by

qulong

FP8 weights

4

#41 opened 30 days ago by

getfit

Update README.md

#40 opened 30 days ago by

mfarre

Update README.md

#39 opened 30 days ago by

mfarre

torch compile compatibility issue

#38 opened 30 days ago by

axiomlab

Sagemaker - How to test the image multimodal?

#37 opened 30 days ago by

TheSuperAgent

Access request got denied

13

#35 opened about 1 month ago by

migtissera

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

#34 opened about 1 month ago by

agam30

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

9

#32 opened about 1 month ago by

krustik

Request: DOI

#31 opened about 1 month ago by

ylx2ai

Couldn't connect

#30 opened about 1 month ago by

Wouze

Ridicolous demands for model gate.

9

#29 opened about 1 month ago by

marksverdhei

🔥🔥🔥中文测评视频

#28 opened about 1 month ago by

leo009

Llama 4 - open-source fine-tuning script

#27 opened about 1 month ago by

hiyouga

Bug in AutoModel

#26 opened about 1 month ago by

random-checkin

pad error

7

8

#25 opened about 1 month ago by

bobber

AWQ version?

15

#24 opened about 1 month ago by

devops724

Object Detection?

#23 opened about 1 month ago by

buckeye17-bah

Thanks zuck

#22 opened about 1 month ago by

WyattTheSkid

converstational?

#21 opened about 1 month ago by

HassanStar

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

10

13

#20 opened about 1 month ago by

UniversalLove333

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

7

#19 opened about 1 month ago by

doaonduty

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

#18 opened about 1 month ago by

getfit

Thanks! Request to access the model rejected due to typo

#17 opened about 1 month ago by

Xinxinli

[request for feedback] Faster downloads with Xet

12

18

#16 opened about 1 month ago by

clem

Thanks!

#15 opened about 1 month ago by

FalconNet

License