Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Kwaipilot
company
https://www.streamlake.ai/product/kat-coder
KwaiAICoder
Activity Feed
Follow
815
AI & ML interests
LLM, AI4SE, Agentic Coding
Recent Activity
liushiyang
new
activity
about 2 months ago
Kwaipilot/KAT-Coder-V2.5-Dev:
最好的35B模型,不输于Qwen3.8-27B
YuanKun-AGI
new
activity
2 months ago
Kwaipilot/KAT-Coder-V2.5-Dev:
Presumably incorrect values from the QWEN original model
liushiyang
new
activity
3 months ago
Kwaipilot/KAT-Coder-V2.5-Dev:
Coverage of Programming Languages in SFT and RL Training
View all activity
Team members
15
Kwaipilot
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Articles
liushiyang
in
Kwaipilot/KAT-Coder-V2.5-Dev
about 2 months ago
最好的35B模型,不输于Qwen3.8-27B
❤️
1
1
#31 opened about 2 months ago by
jgbrblmd
YuanKun-AGI
in
Kwaipilot/KAT-Coder-V2.5-Dev
2 months ago
Presumably incorrect values from the QWEN original model
1
#30 opened 2 months ago by
kalle07
liushiyang
in
Kwaipilot/KAT-Coder-V2.5-Dev
3 months ago
Coverage of Programming Languages in SFT and RL Training
1
#24 opened 3 months ago by
enricos
Is AutoBuilder Open Source?
1
#23 opened 3 months ago by
Behrens
YuanKun-AGI
in
Kwaipilot/KAT-Coder-V2.5-Dev
3 months ago
As a non SWE agentic hobbyist I appreciate this model
❤️
5
2
#21 opened 3 months ago by
GreenMachine87
Does this preserve the scientific and reasoning mind of Qwen3.6 models or does that get scarificed for agentic coding
➕
1
2
#22 opened 3 months ago by
mayankiit04
liushiyang
in
Kwaipilot/KAT-Coder-V2.5-Dev
3 months ago
Do the numbers differ from Ornith and Qwen graphs?
➕
1
11
#1 opened 3 months ago by
hgeist
No difference with base model (for me)...
5
#13 opened 3 months ago by
jbourny
did you train it for 90 rl steps
1
#16 opened 3 months ago by
inikishev
Wrong Qwen3.6-35B-A3B Benchmark
👍
1
2
#17 opened 3 months ago by
XCurOS-35H
Community benchmark results discussion
👍
4
10
#12 opened 3 months ago by
space-spike
Add community evaluation results for SWE-BENCH_VERIFIED, SWE-BENCH_PRO
4
#11 opened 3 months ago by
nielsr
Ricardo-H
in
Kwaipilot/KAT-Coder-V2.5-Dev
3 months ago
Does nobody use dark mode?
➕
4
2
#10 opened 3 months ago by
ercangorgulu
Ricardo-H
updated
a model
3 months ago
Kwaipilot/KAT-Coder-V2.5-Dev
Text Generation
•
35B
•
Updated
Jul 28
•
11.8k
•
671
liushiyang
in
Kwaipilot/KAT-Coder-V2.5-Dev
3 months ago
My experience using and evaluating this model in coding tasks (the results are simply amazing).
👀
❤️
3
3
#6 opened 3 months ago by
Am0gusIsSus
YuanKun-AGI
in
Kwaipilot/KAT-Coder-V2.5-Dev
3 months ago
Parser error with claude code w/ or w/o shared template
3
#5 opened 3 months ago by
xantrk
liushiyang
in
Kwaipilot/KAT-Coder-V2.5-Dev
3 months ago
Parser error with claude code w/ or w/o shared template
3
#5 opened 3 months ago by
xantrk
MTP support? Why no Vision?
20
#3 opened 3 months ago by
unoid
Please specify attention mechanism (how KV cache is treated)
1
#2 opened 3 months ago by
Reverger
Plans for FP8?
👍
3
1
#4 opened 3 months ago by
SRZhu26
Load more