Resources

View closed (5)

Docker file for vllm has been moved

#25 opened 2 days ago by

emanuele-boscari

Update README.md

#23 opened 17 days ago by

bullerwins

Add 'transformers' tag

#22 opened 17 days ago by

betki

Add 'pytorch' tag

#21 opened 17 days ago by

betki

Immaculate

#20 opened 19 days ago by

annettedattolo

Max model len is 32768 when serving with vllm and not 40960

#19 opened 19 days ago by

f14

VLLM Reasoning parser

#17 opened 23 days ago by

Rictus

Model always ends generation with \boxed{}

#16 opened 23 days ago by

cbunivofutah

Model generating non-stop when used in Cline through vLLM

#15 opened 24 days ago by

mhwang093

output issue

#14 opened 24 days ago by

mobo68

No multimodal :c

😔 6

#13 opened 24 days ago by

nicolollo

Greek Language

#12 opened 25 days ago by

myrulezzz

Think token

👀 3

#11 opened 25 days ago by

iyanello

Error with vLLM docker image

#10 opened 25 days ago by

mhwang093

MMMU-Pro Vision with Magistral Small

🔥 ➕ 2

#9 opened 25 days ago by

tomrance

GGUFS (correct) and BF16 - HF , Transformers , with correct tokenizers / json s

🚀 ❤️ 5

#8 opened 25 days ago by

DavidAU

So this is just a SFT "distill" of Magistral-Medium ?

🔥 1

#6 opened 25 days ago by

gghfez

tokenizer

👍 1

#5 opened 26 days ago by

ctranslate2-4you

Missing Tokenizer/Processor for use with Transformers

👍 1

#3 opened 26 days ago by

mgoin

Cool but where Magistral-Medium-2506 weights ?

😔 👍 18

#2 opened 26 days ago by

celsowm