After INTELLECT-1, the globally pre-trained 10B model on 1T tokens, the PI team is tackling globally decentralized post-training. This model, based on QwQ 32B, is an impressive technical achievement. Their technical report goes into more detail.
Specs
Params32B
LicenseApache-2.0
Similarity · VAIL
VAIL Fingerprint
0038:0046:0053:0068:00ac:012c:066c:5f2d
Explore other models with behavioral similarity to INTELLECT-2.
Adoption · Hugging Face
RAM score
—
Hugging Face Downloads
79
last 30d
6.2K
all time
HF Likes
204
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Related Models
