初始化项目，由ModelHub XC社区提供模型

Model: wallfacers/weft-lineage-extractor-0.5b
Source: Original Platform

README.md

@@ -0,0 +1,93 @@
+---
+license: other
+license_name: weft-research
+license_link: https://github.com/wallfacers/data-weave
+pipeline_tag: text-generation
+library_name: transformers
+base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
+datasets:
+- wallfacers/weft-script-lineage-synth
+language:
+- en
+tags:
+- research-artifact
+- negative-result
+- memorization
+- domain-shift
+- data-lineage
+- etl
+- lora
+model-index:
+- name: weft-lineage-extractor-0.5b
+  results:
+  - task:
+      type: table-level-lineage-extraction
+      name: ETL table-level data-lineage extraction
+    dataset:
+      type: synthetic-etl
+      name: synthetic held-out (structural-form isolated)
+    metrics:
+    - type: precision
+      value: 0.994
+      name: Table precision (synthetic held-out)
+  - task:
+      type: table-level-lineage-extraction
+      name: ETL table-level data-lineage extraction
+    dataset:
+      type: real-github-etl
+      name: real GitHub ETL (human gold)
+    metrics:
+    - type: precision
+      value: 0.243
+      name: Table precision (real, out-of-distribution)
+---
+
+# weft-lineage-extractor-0.5b — smallest scale point of a NEGATIVE RESULT
+
+> ## ⚠️ RESEARCH ARTIFACT — the 0.5B point of a *synthetic-only* training study. Not a production tool.
+>
+> ### ✅ Resolved by real data: use **[weft-lineage-extractor-3b](https://huggingface.co/wallfacers/weft-lineage-extractor-3b)** (real corpus, real precision **0.64**). Full study: **[weft-lineage-extractor-1.5b](https://huggingface.co/wallfacers/weft-lineage-extractor-1.5b)**.
+
+The **0.5B** point of a study showing that **synthetic-only training** induces a **verbatim
+memorization leak** in small models for ETL table-lineage extraction. It is the smallest scale
+point and shows the **worst** leak: near-perfect synthetic precision (0.994) collapses to
+**0.243** on real GitHub scripts, with **37.4%** of hallucinations being table names recited
+verbatim from the synthetic training pool.
+
+Same recipe as the [1.5B main model](https://huggingface.co/wallfacers/weft-lineage-extractor-1.5b)
+(LoRA on Qwen2.5-Coder-Instruct, Python/Shell synthetic ETL scripts, zero real scripts); only the
+base size differs.
+
+## This point's numbers (table-level, Convention A)
+
+| metric | synthetic held-out | real GitHub ETL |
+|---|---|---|
+| precision | 0.994 | **0.243** |
+| direction accuracy | — | **0.369** |
+| **verbatim memorization leak** | — | **37.4%** |
+
+## Where it fits (scale curve)
+
+| scale | real precision | real direction | verbatim leak |
+|---|---|---|---|
+| **0.5B (this)** | **0.243** | **0.369** | **37.4%** |
+| 1.5B (main) | 0.270 | 0.496 | 22.4% |
+| 3B (synthetic) | 0.325 | 0.468 | 10.9% |
+| **3B (real corpus)** | **0.64** | — | **~0** |
+
+Leak shrinks with scale (capacity), but only **real training data** closes the real-world gap
+(bottom row). Direction confusion does not improve with size.
+
+## Intended use
+
+- ✅ Reproducing / studying the synthetic-training memorization-leak failure at minimal scale.
+- ❌ Not for production lineage — use the [real-corpus 3B](https://huggingface.co/wallfacers/weft-lineage-extractor-3b).
+
+## Usage, prompt format, training details, citation
+
+Identical to the main model (this variant uses `task_type: PYTHON | SHELL`; everything else the same):
+**[weft-lineage-extractor-1.5b](https://huggingface.co/wallfacers/weft-lineage-extractor-1.5b)**.
+
+- **Dataset & reports:** [wallfacers/weft-script-lineage-synth](https://huggingface.co/datasets/wallfacers/weft-script-lineage-synth)
+- **Base model:** [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct)
+- **Platform:** [Weft (data-weave)](https://github.com/wallfacers/data-weave)