Ashish Vaswani's Essential, which has released a 24T token pre-training dataset in the open before, released an 8B Gemma-like model with strong agentic capabilities. The blog goes into more details why they decided to pre-train models and some of the technical decisions and findings.
Specs
Params8B
LicenseApache-2.0
Tags
Similarity · VAIL
VAIL Fingerprint
02e5:03f0:0617:07c2:0ea5:14ba:2253:56e7
Explore other models with behavioral similarity to rnj-1-instruct.
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
3.4K
last 30d
741.8K
all time
HF Likes
319
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Related Models
