Automated README summary
Automatically summarized from the README on 26 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
CLM-8B is an open System One model that answers typed questions about a state, serving as an alternative to Jev for computer-use, gaming and tool-calling, with up to 9x lower latency.
How it uses Jev
The repo serves CLM-8B behind a TypeSafe-compatible API, so requests written for Jev replay as client.system_one(state, questions). It answers the same Choice and Noul questions, and also supports Score, returning calibrated probabilities used to pick actions or verify candidates.
Primitives:choicenoulscore
Technique worth stealing
Disaggregate states and actions so their embeddings are cached and reused independently, making training and serving cheap and fast.
Try it
pip install contrastive-lm, run vllm serve Qwen/Qwen3-8B, then clm-serve.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectunclear0.54
- Shows a System One patternunclear0.46
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersFound in material0.92
- Is a runnable toolFound in material0.65
- Top-10 learning shortlist signalnot found in the excerpt0.12
- Is a replica of the modelFound in material0.94
- Solves a common problem (0–2)score on a 0–2 scale1.16 / 2
- About JevFound in material0.92
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 26 Sept 2026.