Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
moonshotai
/
Moonlight-16B-A3B-Instruct
like
185
Follow
Moonshot AI
4.96k
Text Generation
Transformers
Safetensors
deepseek_v3
conversational
custom_code
text-generation-inference
arxiv:
2502.16982
License:
mit
Model card
Files
Files and versions
xet
Community
14
Deploy
Use this model
refs/pr/4
Moonlight-16B-A3B-Instruct
/
figures
1.1 MB
6 contributors
History:
1 commit
liushaowei
first commit
391e7a8
10 months ago
banner.png
Safe
48.8 kB
first commit
10 months ago
banner_short.png
Safe
26.9 kB
first commit
10 months ago
chinlaw_8k_flops_ratio.png
Safe
145 kB
first commit
10 months ago
fig_MMLU_performance.png
Safe
225 kB
first commit
10 months ago
fig_weight_decay.png
Safe
416 kB
first commit
10 months ago
logo.png
Safe
13.1 kB
first commit
10 months ago
megatron.png
Safe
1.99 kB
first commit
10 months ago
scaling.png
Safe
224 kB
first commit
10 months ago