An update to the Apriel series, focusing on using fewer tokens per answer while maintaining performance. They achieved this by using GSPO with length and verbosity penalties.
Specs
Params15B
LicenseMIT
Similarity · VAIL
VAIL Fingerprint
0034:0046:0070:00a6:00cd:0120:038a:45a7
Explore other models with behavioral similarity to Apriel-1.6-15B-Thinker.
Resources
Adoption · Hugging Face
RAM score
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Hugging Face Downloads
5.7K
last 30d
25.6K
all time
HF Likes
305
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Related Models
