Resources

View closed (20)

doc: add link for paper and github repo

#53 opened about 6 hours ago by

FuryMartin

Model not generating </think> token .

➕ 5

#52 opened about 8 hours ago by

pratiknarola

Add MMLU-Pro evaluation results

#51 opened about 8 hours ago by

nielsr

Add GPQA diamond evaluation results

#50 opened about 8 hours ago by

nielsr

Add HLE evaluation results (with tools)

#49 opened about 8 hours ago by

nielsr

The content of response from Kimi-K2.5 is empty when deploying with vllm-0.15.0.

#40 opened 1 day ago by

tuo02

AttributeError: 'CompressedLinear' object has no attribute 'weight'

#39 opened 1 day ago by

xbeark

Kimi K2.5 claims to be Claude, behaves like it, and even references Anthropic's Constitutional AI.

🤗 👀 7

#38 opened 1 day ago by

ombd

Update chat template to use reasoning if reasoning_content is unavailable, which is deprecated

#37 opened 2 days ago by

koushd

fix: wrong return type annotation in resampling() function

#36 opened 2 days ago by

ThanhNguyxn

fix: type annotation bugs in media_utils, processor and config

#35 opened 4 days ago by

ThanhNguyxn

fix: bugs and improvements

#34 opened 4 days ago by

ThanhNguyxn

Can it be added to microsoft foundry please?

#32 opened 5 days ago by

atootikhos4

返回的内容为claude的思考过程的数据格式

🤗 👍 3

#30 opened 5 days ago by

tzzhangyajun

Kimi K2.5 using ktkernel + sglang, 16 TPS, but no starting <think> tag.

➕ 1

#28 opened 6 days ago by

gyularabai

Where is the mecord?

#25 opened 6 days ago by

luoxlong

Request: DOI

#23 opened 7 days ago by

torouni

bug: tools with dashes in their name

➕ 2

#22 opened 7 days ago by

koushd

Need speed estimate on 6x H200

#21 opened 7 days ago by

mechanicmuthu

Guide to run Kimi K2.5 locally on your device.

😔 🤯 7

#19 opened 7 days ago by

shimmyshimmer

Observing (no content) response from the model randomly

➕ 1

#18 opened 7 days ago by

shivamashtikar

Can the BrowseComp results be reproduced?

👍 2

#17 opened 7 days ago by

Aldrich-x

Could I deploy the model with 8XA100？

#15 opened 7 days ago by

mio

is K2.5 the same as K2.5 Thinking?

👍 1

#14 opened 7 days ago by

Lord-Shibe

Context Management Reproducibility | 可复现性 ?

👀 👍 6

#13 opened 8 days ago by

pandemo

Code for agent swarm?

👍 1

#10 opened 8 days ago by

nxphi47

Slow Tokenizer Issue

#7 opened 8 days ago by

pratiknarola

Should `rope_scaling.beta_fast` be `1.0`?

#6 opened 8 days ago by

jukofyork

Congratulations on this release and on one important realization!

🔥 👍 19

#5 opened 8 days ago by

Dampfinchen

Do you have any related native multimodal architecture diagrams?

👍 1

#4 opened 8 days ago by

jackkuo

Good work! just a question about model attention architecture

#3 opened 8 days ago by

alexjadone