Ling-mini-2.0
General purpose
The Ant Group continues to fly under the radar, but this release is pretty interesting in our opinion: They train relatively small MoE models with only 16B total parameters, but they share different checkpoints during the training for 5, 10, 15 and 20 trillion tokens. Furthermore, they release patches for Megatron and TransformerEngine and guides how to train the models further. On top of all of that, they also release a reasoning version.
Specs
Params16B (1.4B active)
LicenseMIT
Similarity · VAIL
VAIL Fingerprint
0033:0052:0079:00de:0112:0183:0621:59b0
Explore other models with behavioral similarity to Ling-mini-2.0.
Capability · Artificial Analysis
AA Index
3.4
Adoption · Hugging Face
RAM @ 30d
Relative Adoption Metric: 0.01×. Below benchmark. Measured at 30 days.
Hugging Face Downloads
17.1K
last 30d
223.5K
all time
HF Likes
198
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Related Models
