jeff-adapter-legal-clauses

Contract clause types. Labels a single contract provision with its clause type, such as governing law, notices or confidentiality.

A LoRA adapter for jeff-base v1.3, a small open decision model (a fine-tune of Qwen3.5-0.8B). You send a situation (the state) and questions with named options; Jeff returns a calibrated probability for every option from one forward pass, with no generated text to parse. One Jeff server loads the base once and any number of adapters beside it; each request picks an adapter by name ("model": "legal-clauses").

Adapter page, with the full data card: jeffhub.ai/adapters/legal-clauses.

Results

On this adapter's held-out test sets, never trained on, scored three ways on the same rows: the untrained model Jeff is built from, the Jeff v1.3 base alone, and the base with this adapter. Every question has 100 options. As of 2026-10-05. All adapters

Test set	Test rows	Qwen3.5-0.8B untrained	Jeff base v1.3 alone	Jeff base v1.3 + adapter
test	9,895	12.5% · 0.094	7.4% · 0.039	83.6% · 0.011
test-novel	7,357	12.1% · 0.090	7.1% · 0.044	81.4% · 0.015

Each cell: accuracy · calibration error (ECE; lower is better, 0 is perfect).

test.jsonl in this repository is the test set; test-novel is not included.

With llama.cpp (GGUF)

The same test, through llama.cpp: the base GGUF (mstrasser/jeff-base-gguf) plus this adapter's LoRA GGUF (mstrasser/jeff-adapter-legal-clauses-gguf), with the temperature refitted for each format. Running Jeff with llama.cpp

Test set	Full precision	Q8_0	Q4_K_M
test	83.6% · 0.011	83.8% · 0.011	83.4% · 0.010
test-novel	81.4% · 0.015	81.6% · 0.015	81.2% · 0.015

Not measured yet for v1.3: calibration charts, the commonest confusions and accuracy per answer.

Source of these numbers: results/sources/v1.3/retrained-adapters.table.json in the JeffHub repository, also collected in jeffhub-v1.3.json.

When to use it

• You have a contract split into provisions and want each one labelled with a clause type.
• Your contracts are commercial or employment agreements written in English, like those filed with the US SEC.
• You can use the 100 LEDGAR clause types, or a subset of them, as your options.

When not to use it

• Your contracts are not in English, or follow a legal system very different from the US. All training text comes from US SEC filings.
• You need legal advice or a judgement on whether a clause is fair or enforceable. The adapter only names the clause type.
• You pass a whole contract at once. It was trained on one provision at a time.
• You need your own clause types. Training used the LEDGAR labels only.

How to use it

The adapter runs with Jeff's server, on the main branch of firelex/jeff, on the jeff-base v1.3 base.

git clone https://github.com/firelex/jeff && cd jeff
uv sync --no-default-groups --extra lora          # add --extra cuda on NVIDIA GPUs, --extra mac on Apple silicon
uv run --no-default-groups hf download mstrasser/jeff-base --revision v1.3 --local-dir checkpoints/jeff-base
uv run --no-default-groups hf download mstrasser/jeff-adapter-legal-clauses --revision v1.3 --local-dir adapters/legal-clauses
JEFF_CHECKPOINT=checkpoints/jeff-base JEFF_ADAPTERS=adapters/ PORT=8765 \
  uv run --no-default-groups jeff-serve          # on a Mac, add JEFF_BACKEND=mlx

Every folder in adapters/ is served under its folder name; add or replace adapters while the server runs with curl -X POST http://localhost:8765/v1/adapters/reload. Each adapter records the exact base it was trained on, and the server refuses an adapter trained on a different one, so this adapter loads only on jeff-base v1.3 (a v1.2 adapter does not load on v1.3). For llama.cpp, use mstrasser/jeff-adapter-legal-clauses-gguf.

Request format

State (the situation), in this order:

Key	Changes per request	What it holds
document	no	One sentence about the document the provision comes from. In training this was always "A commercial contract filed with the U.S. Securities and Exchange Commission (SEC)".
provision	yes	The text of one contract provision.

Questions:

• clause_type (choice): Which type of clause the provision is, judged by its main topic. Options: 100 LEDGAR clause types, each with a snake_case key such as governing_laws and a one-line description. The full list is LEDGAR in descriptions.py in the source.

Rules:

• Use the option keys and descriptions from descriptions.py; the adapter was trained on them.
• Several clause types are close in meaning (for example assignments and assigns). Expect probability to be shared between them.
• Use the instructions below word for word; the adapter was trained mostly on them.

General rules for every request: the request format guide.

Example

The request below is also in this repository as example.json.

{
  "model": "legal-clauses",
  "state": {
    "document": "A commercial contract filed with the U.S. Securities and Exchange Commission (SEC)",
    "provision": "This Agreement shall be governed by and construed in accordance with the laws of the State of Delaware, without regard to its conflict of laws principles."
  },
  "questions": {
    "clause_type": {
      "type": "choice",
      "instructions": "Which type of clause is this contract provision? Choose the clause type that best matches the main topic of the provision.",
      "criteria": {
        "governing_laws": "Governing law: which state's or country's law governs the contract.",
        "notices": "Notices: how formal notices must be given, and to which addresses.",
        "confidentiality": "Confidentiality: keeping information secret and limits on using or disclosing it.",
        "terminations": "Termination: how and when the contract or employment can be ended, and what follows.",
        "assignments": "Assignments: whether and how a party may transfer its rights or duties under the contract to someone else.",
        "severability": "Severability: if one provision is invalid, the rest of the contract remains in force.",
        "entire_agreements": "Entire agreement: the contract is the whole agreement and replaces all earlier agreements on the subject.",
        "indemnifications": "Indemnification: one party must compensate and defend the other against losses and claims.",
        "counterparts": "Counterparts: the contract may be signed in separate copies, including electronic signatures, which together form one agreement.",
        "waiver_of_jury_trials": "Waiver of jury trial: the parties give up the right to a jury trial in disputes.",
        "amendments": "Amendments: how the contract can be amended, usually only in writing signed by the parties."
      }
    }
  }
}

curl -s localhost:8765/v1/systemone -H 'content-type: application/json' -d @adapters/legal-clauses/example.json

The answer holds a probability for each option of each question. A recorded response from the v1.3 adapter is not published yet.

Files

• adapter_model.safetensors, adapter_config.json: the LoRA weights (PEFT format);
• readout.safetensors: the adapter's own readout over the answer codes;
• decision_config.json: answer codes, temperature, prompt layout and the checksum of the base it was trained on;
• test.jsonl: the held-out test set the results below were measured on;
• calibration.jsonl: the calibration rows the adapter's temperature was fitted on;
• example.json: the example request above.

adapter_config.json and decision_config.json name the base as mstrasser/jeff-base, revision v1.3; the server checks the base by the checksum of its weights.

Training

Base	mstrasser/jeff-base, revision v1.3 (a fine-tune of Qwen3.5-0.8B)
Prompt layout	live-last: the fixed part of the request first, the changing state field last
Training code	The git_commit recorded in decision_config.json is the training machine's copy and was not published. It builds exactly the same prompt as main of firelex/jeff (from commit 6d0d7da) for a text state and for an object with at least one field; the format is in docs/v1.3-request-format.md
Run	0.8b-legal-clauses-20261003-0149, final checkpoint
Adapter files	41.5 MB (adapter_model.safetensors and readout.safetensors)
LoRA GGUF for llama.cpp	mstrasser/jeff-adapter-legal-clauses-gguf

• 1.3.0 (2026-10-03): Trained on Jeff v1.3 with the live-last prompt layout (LoRA rank 16, one epoch, about 10% of the base model's own training data mixed in).

Data card

Report attached. The shortcut report and data card are included and pass the JeffHub checks; the numbers are the maintainers’ own. What the levels mean

• Test set: included in this repository as test.jsonl, so anyone can check the numbers
• Calibration rows: included in this repository as calibration.jsonl, the rows its threshold is chosen on
• QA report, sanitised: the data-quality checks run before training

How the test set was held out. The official LEDGAR test split, as distributed in LexGLUE; never trained on.

Training data. Built from public data sets, listed under Data and licence.

The attached QA report was written for the data of the previous release; the v1.3 data fixes the notes it left open. The QA report re-run on the v1.3 data is still to be attached.

The source data sets are public (listed under Data and licence). A script to rebuild our rows from them will follow.

Near-duplicate provisions (standard boilerplate) appear at most three times in training, which leaves 61,848 training rows.

Training mixed in a replay sample of the Jeff base model's own training data: 6,185 rows, about 10% on top of the adapter's 61,848 (inherited from the v1.2 recipe as a precaution; its effect has not been measured).

Data and licence

Adapter licence: Apache-2.0.

Qwen3.5-0.8B notice: these weights were modified from Qwen3.5-0.8B by the Jeff project: jeff-base is a fine-tune of Qwen3.5-0.8B, and this adapter was trained on top of it. Qwen3.5-0.8B is Copyright 2026 Alibaba Cloud and licensed under the Apache License, Version 2.0; a copy of that licence is in LICENSE.

It was trained on:

• LEDGAR (LexGLUE ledgar configuration). Licence: CC-BY-4.0 (open licence)

  Provisions are from public SEC EDGAR filings (Tuggener et al. 2020). Option descriptions were written by hand from the label names.

Limitations

• Tied to jeff-base v1.3. It will not load on any other base or version; the server checks the base weights' checksum.
• Jeff chooses between the options you give it. It does not write text or reason in several steps.
• Calibration was fitted on this adapter's own calibration rows. On very different data, check it again.
• Everything listed under When not to use it above.

Links

• Adapter page: jeffhub.ai/adapters/legal-clauses
• Base model: mstrasser/jeff-base (revision v1.3)
• LoRA GGUF for llama.cpp: mstrasser/jeff-adapter-legal-clauses-gguf
• What changed in v1.3: release notes
• Code and server: github.com/firelex/jeff

Jeff is an independent project. It uses the same request format as Jev but is not affiliated with or endorsed by TypeSafe, the makers of Jev.