Resources

View closed (6)

mmlu评测和if_eval结果

#32 opened about 3 hours ago by

cloudcc

Issues with Structured Output

#31 opened about 2 months ago by

LinYouyIFAD

请问下如果想微调能给个案列吗？

#30 opened 2 months ago by

wa595566

Exceptional Release, This is The Most Powerful OSS Model for 24GB Cards

👍 4

#29 opened 3 months ago by

AaronFeng753

super bad german

#28 opened 3 months ago by

abiteddie

Prevent tokenizer calls from returning `token_type_ids`

❤️ 1

#26 opened 3 months ago by

joaogante

Hiding Thinking Process

#25 opened 4 months ago by

Xzendor7

Draft model for speculative decoding

#24 opened 4 months ago by

oobabooga

这模型数学能力很强

#23 opened 4 months ago by

pypry

Suppose I have 96g vram is it possible to do fine tuning?

#22 opened 4 months ago by

win10

Would love to see coding version :)

👍 2

#21 opened 4 months ago by

AekDevDev

chat_template：it keeps all thinking content?

#20 opened 4 months ago by

TAnGx1411

Getting error when deploying on HF Inference with 2 A100 GPU's of AWS on region us-east

#19 opened 4 months ago by

streebo

FP8 Quants Please

➕ 1

#18 opened 4 months ago by

rjmehta

online demo please

👍 1

#15 opened 4 months ago by

pypry

vram Requirements for full size

#14 opened 4 months ago by

tazomatalax

demo Inference

➕ 2

#13 opened 4 months ago by

devops724

salut

#12 opened 4 months ago by

CripVL

bug in chat template?

#11 opened 4 months ago by

J22

Why is the chat_template mixed with Chinese and English?

👍 2

#8 opened 4 months ago by

Daucloud

is docker image available?

#7 opened 4 months ago by

ZhifengKong

Deployment support for sglang

👍 3

#5 opened 4 months ago by

XiChen0415

vllm error:operator _C::marlin_qqq_gemm does not exist

#4 opened 4 months ago by

HourseCircle

Category Error

👍 1

#3 opened 4 months ago by

CO-IR

Sorry for Askin here

👀 5

#2 opened 4 months ago by

ryg81

Official vllm support

👀 2

#1 opened 4 months ago by

shash42