Note Start here: try the 2B in your browser. Your own text and question, a probability for every option. No install needed.

chaoliangUNSW/Jev-Style-2B-Decision-v3

Text Classification • 2B • Updated 4 days ago • 108 • 3

Note 2B main model (PyTorch, bf16 safetensors, 3.76 GB) with the runtime, full results and protocols.

chaoliangUNSW/Jev-Style-2B-Decision-v3-GGUF

Text Classification • 2B • Updated 4 days ago • 776 • 5

Note 2B for llama.cpp, with the bundled jev-score-v2 scorer: F16 3.78 GB, Q8_0 2.01 GB, Q4_K_M 1.27 GB.

chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX

Text Classification • Updated 4 days ago • 181 • 1

Note 2B for Apple silicon: bf16 (3.76 GB) and 8-bit (2.00 GB) in one repo.

chaoliangUNSW/Jev-Style-0.8B-Decision-v3

Text Classification • 0.8B • Updated 4 days ago • 404 • 4

Note 0.8B main model (transformers, full precision) with quick start, full results and protocols.

chaoliangUNSW/Jev-Style-0.8B-Decision-v3-GGUF

Text Classification • 0.8B • Updated 5 days ago • 2.09k • 11

Note 0.8B for llama.cpp: F16, Q8_0 and Q4_K_M. Smallest download: 0.53 GB (Q4_K_M).

chaoliangUNSW/Jev-Style-0.8B-Decision-v3-MLX

Text Classification • Updated 5 days ago • 1

Note 0.8B for Apple silicon: 8-bit (0.80 GB) and bf16 (1.50 GB) in one repo.

Note Try the 0.8B in your browser: your own text and question, a probability for every option. No install needed.

Note 0.8B use-case demos: triage, email, guardrails, RAG filter, moderation, routing, 51 languages, long documents, agent approval. Each tab turns the probabilities into an action and shows the rule.