commit 6d75293cb1c9c5445363f73085811f7ead348dd2 Author: ModelHub XC Date: Sat Jul 18 07:26:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: wallfacers/weft-lineage-extractor-jvm-1.5b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a42203c --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +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-1.5B-Instruct +datasets: +- wallfacers/weft-script-lineage-synth +language: +- en +tags: +- research-artifact +- negative-result +- memorization +- domain-shift +- cross-language +- data-lineage +- etl +- lora +model-index: +- name: weft-lineage-extractor-jvm-1.5b + results: + - task: + type: table-level-lineage-extraction + name: ETL table-level data-lineage extraction (Scala/Java) + dataset: + type: real-jvm-etl + name: real Scala/Java ETL (human gold, n=141) + metrics: + - type: precision + value: 0.165 + name: Table precision (real JVM, out-of-distribution) + - type: accuracy + value: 0.418 + name: Read/write direction accuracy (real JVM) +--- + +# weft-lineage-extractor-jvm-1.5b — cross-language reproduction of a NEGATIVE RESULT + +> ## ⚠️ RESEARCH ARTIFACT — the Scala/Java (JVM) 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 **JVM (Scala/Java)** point of a study showing that **synthetic-only training** induces a +**verbatim memorization leak** in small ETL table-lineage models — and that the failure +**reproduces, worse, across languages**. Synthetic held-out looks near-perfect (~0.99); on real +Scala/Java ETL it drops to **precision 0.165**, with **40.8%** of hallucinations being table names +recited verbatim from the synthetic training pool — the **highest leak** of all scale/language +points, because real JVM code is the most out-of-distribution. + +Same recipe as the [1.5B main model](https://huggingface.co/wallfacers/weft-lineage-extractor-1.5b) +(LoRA on Qwen2.5-Coder-1.5B), extended with synthetic Scala/Java forms; `task_type: SCALA | JAVA`. + +## This point's numbers (table-level, Convention A) + +| metric | synthetic held-out | real Scala/Java ETL (n=141, non-empty 28) | +|---|---|---| +| precision | ~0.99 | **0.165** | +| direction accuracy | — | **0.418** | +| **verbatim memorization leak** | — | **40.8%** | + +The leak metric is **gold-independent** and stable to full-file re-adjudication (verbatim +40.4% → 40.8%). Given a real `SqlDao.java` it cannot parse, the model emits training-pool names +like `dws.dws_member_point_df` — memorized generator vocabulary, not a label artifact. + +## Where it fits (scale / cross-language curve) + +| point | real precision | real direction | verbatim leak | +|---|---|---|---| +| 0.5B (Py/Sh) | 0.243 | 0.369 | 37.4% | +| 1.5B (Py/Sh) | 0.270 | 0.496 | 22.4% | +| 3B (Py/Sh, synthetic) | 0.325 | 0.468 | 10.9% | +| **1.5B + JVM (this, real JVM)** | **0.165** | **0.418** | **40.8%** | +| **3B (real corpus)** | **0.64** | — | **~0** | + +"Add another language" does not fix the real-world gap; **real training data does**. + +## Intended use + +- ✅ Reproducing / studying the cross-language reproduction of the memorization-leak failure. +- ❌ 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 adds `task_type: SCALA | JAVA` and JVM system-prompt wording): +**[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-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) +- **Platform:** [Weft (data-weave)](https://github.com/wallfacers/data-weave) diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..71f1835 --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.5.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9e9ebf8 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.1, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.5.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..7b55584 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f98ffdc5a077702fd5aca5a4076e09327ae987cec6cb053547b60f1ff695dbb2 +size 3087467144 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..e4fb8c3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}