Upload folder using huggingface_hub

README.md

@@ -1,231 +1,9 @@
 ---
-license: apache-2.0
-license_link: https://www.apache.org/licenses/LICENSE-2.0
-language:
-- en
 library_name: mlx
-base_model: mlx-community/Qwen3-1.7B-4bit
-base_model_relation: finetune
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE
 pipeline_tag: text-generation
+base_model: mlx-community/Qwen3-1.7B-4bit
 tags:
 - mlx
-- qwen3
-- legal
-- law
-- thin-language-model
-- lens
-- lora
-- 4-bit
-- apple-silicon
-- text-generation
-- conversational
-widget:
-- text: "Summarize the holding of the following case:\n\n<paste judgment text>"
----
-
-<div align="center">
-
-<img src="https://huggingface.co/FahrenheitResearch/FR-Lex-1.7B/resolve/main/assets/banner.jpeg" alt="Fahrenheit Research" width="100%">
-
-# FR-Lex-1.7B
-
-**A Thin Language Model for law. Grounded, jurisdiction-aware, and running on your laptop.**
-
-`GROUNDED.` &nbsp; `JURISDICTIONAL.` &nbsp; `LOCAL.`
-
-<p>
-<a href="https://www.apache.org/licenses/LICENSE-2.0" target="_blank" style="margin:2px;"><img alt="License" src="https://img.shields.io/badge/License-Apache_2.0-D4F23C?style=flat-square&labelColor=0D0D0D" style="display:inline-block;vertical-align:middle;"></a>
-<img alt="Base" src="https://img.shields.io/badge/Base-Qwen3--1.7B-1A1A1A?style=flat-square&labelColor=0D0D0D" style="display:inline-block;vertical-align:middle;">
-<img alt="Format" src="https://img.shields.io/badge/MLX_·_4--bit-1A1A1A?style=flat-square&labelColor=0D0D0D&logo=apple&logoColor=D4F23C" style="display:inline-block;vertical-align:middle;">
-<img alt="Domain" src="https://img.shields.io/badge/Domain-Legal-D4F23C?style=flat-square&labelColor=0D0D0D" style="display:inline-block;vertical-align:middle;">
-<a href="https://f-r.co" target="_blank" style="margin:2px;"><img alt="Website" src="https://img.shields.io/badge/Website-f--r.co-D4F23C?style=flat-square&labelColor=0D0D0D" style="display:inline-block;vertical-align:middle;"></a>
-<a href="https://github.com/fahrenheit-research" target="_blank" style="margin:2px;"><img alt="GitHub" src="https://img.shields.io/badge/GitHub-fahrenheit--research-1A1A1A?style=flat-square&labelColor=0D0D0D&logo=github&logoColor=white" style="display:inline-block;vertical-align:middle;"></a>
-<a href="https://huggingface.co/FahrenheitResearch/FR-Forge-1.7B" target="_blank" style="margin:2px;"><img alt="Sibling" src="https://img.shields.io/badge/Sibling-FR--Forge_1.7B-1A1A1A?style=flat-square&labelColor=0D0D0D" style="display:inline-block;vertical-align:middle;"></a>
-</p>
-
-</div>
-
----
-
-## Contents
-
-1. [Overview](#overview)
-2. [How it works](#how-it-works)
-3. [Specifications](#specifications)
-4. [Quickstart](#quickstart)
-5. [Intended use](#intended-use)
-6. [Coverage](#coverage)
-7. [Limitations](#limitations)
-8. [Training](#training)
-9. [Citation](#citation)
-
-## Overview
-
-FR-Lex-1.7B is a **Thin Language Model (TLM)** for law, by Fahrenheit Research. Sibling to [FR-Forge](https://huggingface.co/FahrenheitResearch/FR-Forge-1.7B) (manufacturing). It is a small, 4-bit, MLX model fine-tuned with LoRA adapters on a balanced, multi-jurisdiction legal corpus, designed to run locally on Apple Silicon.
-
-It is built to **process legal text you give it**, not to recall case law from memory. Version 0.2 covers the United States and Australia as primary jurisdictions, with experimental German and Swedish support.
-
-```text
-  Where a Thin Language Model fits
-
-  specialization
-     ▲
-     │   ● FR-Lex 1.7B
-     │     narrow · local · cheap
-     │
-     │                              ● Frontier LLM
-     │                                broad · hosted · costly
-     └──────────────────────────────────────────────▶ generality
-```
-
-## How it works
-
-FR-Lex runs **standalone** for narrow legal tasks, or as a **Lens** that sits in front of a larger general LLM, enriching a query before the expensive computation.
-
-```text
-  Court document / legal query
-            │
-            ▼
-  ┌─────────────────────────────────────────────────────┐
-  │ FR-Lex 1.7B                                           │
-  └─────────────────────────────────────────────────────┘
-            │
-   ┌────────┴─────────┐
-   ▼                  ▼
-  STANDALONE        LENS (enrich, then route)
-   │                  │
-   ├─ summarize       ├─ detect jurisdiction
-   ├─ extract holding ├─ extract citations
-   ├─ spot issues     └─▶  Frontier LLM  (expensive reasoning)
-   └─ explain plainly
-            │
-            ▼
-   Grounded, local answer  (supply the source text for factual output)
-```
-
-It is an assistant, not a certified authority. It is not a substitute for a licensed attorney or the controlling law.
-
-## Specifications
-
-| | |
-|---|---|
-| **Base** | Qwen3-1.7B (4-bit, MLX) |
-| **Parameters** | 1.7B · 4-bit |
-| **Method** | LoRA adapters, fused |
-| **Runtime** | MLX (Apple Silicon) |
-| **Languages** | English (DE / SV experimental, answers in source language) |
-| **Version** | 0.2 |
-| **License** | Apache-2.0 |
-
-## Quickstart
-
-Runs locally with MLX on Apple Silicon. Supply the source text as context for factual output.
-
-```bash
-pip install -U mlx-lm
-python3 -m mlx_lm generate \
-  --model FahrenheitResearch/FR-Lex-1.7B \
-  --max-tokens 400 \
-  --prompt "Summarize the holding of the following case:
-
-<paste judgment text>"
-```
-
-```python
-from mlx_lm import load, generate
-
-model, tok = load("FahrenheitResearch/FR-Lex-1.7B")
-prompt = "Summarize the holding of the following case:\n\n<paste judgment text>"
-print(generate(model, tok, prompt=prompt, max_tokens=400))
-```
-
-Pin a specific release with `load("FahrenheitResearch/FR-Lex-1.7B", revision="v0.1")`.
-
-## Intended use
-
-Grounded legal-text processing over court documents:
-
-```text
-  FR-Lex covers
-  ├─ Grounded summarization     condense judgments and filings
-  ├─ Holding extraction         isolate the operative ruling
-  ├─ Issue spotting             flag the legal questions at stake
-  ├─ Plain-language explanation translate legalese for non-lawyers
-  └─ Citation extraction        pull and normalize references
-```
-
-Best results come from supplying the source text as context.
-
-## Coverage
-
-```text
-  Jurisdiction maturity  (qualitative tiers, not a benchmark)
-
-  United States   ████████████████████  primary · strongest
-  Australia       ████████████████████  primary · strongest
-  Germany         ███████████░░░░░░░░░░  experimental
-  Sweden          ███████░░░░░░░░░░░░░░  experimental · weakest
-  India           ████░░░░░░░░░░░░░░░░░  pipeline only (not in weights)
-  UAE             ████░░░░░░░░░░░░░░░░░  pipeline only (not in weights)
-```
-
-- **United States, Australia** — primary, strongest quality.
-- **Germany, Sweden** — experimental; answers in the source language. German is more reliable than Swedish (whose open corpus mixes in EU translations).
-- **India, UAE** — supported in the pipeline (citation and jurisdiction detection) but not yet in these trained weights.
-
-## Limitations
-
-> **Not legal advice.** Outputs are legal information for research and drafting assistance only. Consult a licensed attorney.
-
-- **Experimental European coverage.** German and Swedish are early; German is more reliable than Swedish. India and the UAE are in the pipeline but not yet in these trained weights.
-- **Not a knowledge base.** Ungrounded recall will confabulate; always supply the source text for factual output.
-- **Small model.** For anything that must be exact (clause text, citation strings), verify against the controlling source.
-
-## Training
-
-```text
-  Multi-jurisdiction legal corpus ─┐
-  US caselaw (CAP / Common Pile)    │
-  Open Australian Legal Corpus      ├─▶ LoRA fine-tune (MLX) ─▶ fuse adapters ─▶ FR-Lex 1.7B
-  German court decisions (OLD)      │     balanced across jurisdictions
-  Swedish SweLaw corpus            ─┘
-```
-
-<details>
-<summary>Base, method, data, and targets</summary>
-
-- **Base model:** `mlx-community/Qwen3-1.7B-4bit` (Qwen3 architecture, 4-bit), fine-tuned with LoRA via MLX on Apple Silicon.
-- **Data, by source license:**
-  - Public-domain US caselaw — Caselaw Access Project via the Common Pile.
-  - Open Australian Legal Corpus — CC BY 4.0.
-  - German court decisions — Open Legal Data, MIT.
-  - Swedish SweLaw corpus — CC0.
-  - Balanced across the four jurisdictions.
-- **Targets:** teacher-distilled summaries, holdings, issues, and plain-language explanations; rule-based citation targets.
-
-</details>
-
-## Citation
-
-Apache-2.0. Base model `mlx-community/Qwen3-1.7B-4bit` is Apache-2.0. Built on Qwen3 (Alibaba Cloud, Apache 2.0). Training data per source licenses; see the project repository for full attribution.
-
-```
-@software{fr_lex_2026,
-  title  = {FR-Lex-1.7B: a thin language model for law},
-  author = {Fahrenheit Research},
-  year   = {2026},
-  note   = {Fine-tuned from Qwen3-1.7B (4-bit) with MLX/LoRA}
-}
-```
-
 ---
-
-<div align="center">
-
-**FAHRENHEIT RESEARCH**
-
-Thin Language Models for specialized domains.
-
-[Website](https://f-r.co) &nbsp;·&nbsp; [GitHub](https://github.com/fahrenheit-research) &nbsp;·&nbsp; [Sibling model: FR-Forge-1.7B](https://huggingface.co/FahrenheitResearch/FR-Forge-1.7B)
-
-</div>

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db913a37b1081e36b177caf71e01d47aab968d29820d5e1cbdfca1abe85eee47
+oid sha256:a2140c66d0d44447beacc41eb74c1ce4056c9e62de637665cad11eb07201f366
 size 968080210