No official torrent yet β requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from IFM/K2-Type-0.9B
All models by IFM βA 0.9B decision model in the style of TypeSafe's Jev (K2-Horizon-0.9B backbone; 1.08B parameters stored, including the base model's unused language-model head). You send one state (text or JSON) and any number of typed questions; it returns a probability for every option of every question from one forward pass. It never generates text.
Questions share the state but cannot see each other (block-causal attention mask), so adding a question never changes another's answer. Built on IFM/K2-Horizon-0.9B.
JevBench public set (231 items, jevbench commit 26eb72d,
typesafe adapter against this repo's server, one H200, no network):
Brier 0.328, ECE 0.065; latency p50 27 ms, p95 60 ms per decision; mean 590 input tokens per decision. For reference, public accuracy on the JevBench v1.4 board: Gemma 4 E2B + LoRA (system-one-open) 0.732, decider-2b 0.710, kev 0.6B 0.667, kev 4B 0.662, Qwen3.5-4B entries 0.74-0.82, Jev 1.13.0 0.866. The official JevBench score also uses sealed items; every listed system scores well below its public accuracy there.
Snake: the same weights play Snake from a text board (one choice + four yes/no questions per move): 66 food per game on 12x12 on average (max 101).
The first request after start-up takes a few seconds (CUDA warm-up); later requests take about 20-60 ms.
The request and response follow TypeSafe's /v1/systemone wire format, so clients written for Jev or Kev work
unchanged. GET /health reports the model name and temperature.
This repository contains the weights and the minimal code needed to serve them (jev/: input encoding, the pointer
head, and the HTTP server). Training code and data are not released at this time.
Requires transformers >= 5.17 (remote code); tested on torch 2.8. Do not use the backbone for text generation: its weights were trained
for the decision head, and the language-model head is left from the base model. Use the jev/ server.
<state> ... | <q> question <opt> option </opt> ... <decide> | <q> ..., using five reserved tokens of
the base tokenizer (decision_config.json).pointer_head.safetensors) scores each option's </opt> hidden state against the question's
<decide> hidden state; a softmax at temperature 1.478 gives the probabilities.pip install -U huggingface_hubhf download IFM/K2-Type-0.9B --local-dir K2-Type-0.9B && cd K2-Type-0.9Bpip install -r requirements.txtpython -m jev.serve --run . --port 8000 # from this repo's root; needs one CUDA GPUcurl -s localhost:8000/v1/systemone -H 'Content-Type: application/json' -d '{ "state": {"subject": "Charged twice", "body": "You billed my card twice for March. Refund one or I cancel."}, "questions": { "queue": {"type": "choice", "instructions": "Which queue handles this?", "criteria": {"billing": "Payments and refunds", "technical": "Bugs and login", "general": "Anything else"}}, "angry": {"type": "noul", "instructions": "The customer sounds angry."}, "urgency": {"type": "score", "instructions": "How urgent is it?", "criteria": ["Low", "Normal", "High", "Critical"]} }}'