Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+base_model: mlx-community/Qwen3.5-9B-4bit
+library_name: mlx
+license: other
+license_name: qwen
+tags:
+- lora
+- ontology-learning
+- ontology-extraction
+- text2onto
+- llms4ol-2026
+- qwen3.5
+---
+
+# qwen3.5-9b-ontology-extraction-baseft-mlx
+
+A LoRA adapter for **`Qwen/Qwen3.5-9B`** that extracts a *primitive ontology* — `[subject,
+relation, object]` triples — from a raw text document.
+
+Built by **Semantic Swingers** for the **LLMs4OL 2026** shared task (Task A, "flagship":
+text → ontology triples, scored by graph similarity). If you have not heard of the challenge, the
+short version: given a document, produce the taxonomy/typing triples it implies. This adapter is the
+fine-tuned generator behind our submission.
+
+## Which adapter is this
+
+- **Regime:** base-FT (no exemplars).
+- **Use `top_k = 0` at inference.** base-FT was trained without exemplars, so it is best run retrieval-free. Using the wrong `k` understates the adapter.
+- **Hardware:** Apple Silicon (MLX). Runs natively on Apple Silicon via MLX.
+
+- **Score:** this is the Apple-Silicon 4-bit MLX variant, a *separate artifact* from the bf16 champions — its score differs and is **not** the reported number.
+
+## How to run it
+
+Through our OntoLearner integration (the learner ships in the fork below):
+
+```python
+from ontolearner.learner.text2onto import SemanticSwingersText2OntoLearner
+
+learner = SemanticSwingersText2OntoLearner(
+    adapter="datagero/qwen3.5-9b-ontology-extraction-baseft-mlx",
+    base_model_id="mlx-community/Qwen3.5-9B-4bit",
+    backend="mlx",
+    top_k=0,
+)
+learner.load()
+# learner.fit(train_docs, task="text2onto"); learner.predict(eval_docs, task="text2onto")
+```
+
+## How it was made (the training code is part of the integration)
+
+This adapter was produced by the **same package** that serves it — training is a first-class part
+of the OntoLearner integration, not a separate script:
+
+- **Training code:** [`semanticswingers_train.py`](https://github.com/matias-vizcaino/OntoLearner-semanticswingers/blob/feat/semanticswingers-llms4ol2026/ontolearner/learner/text2onto/semanticswingers_train.py) — LoRA SFT with prompt masking
+  (loss on completion tokens only) and, for RA-FT, **leave-one-out** exemplar retrieval so a
+  training document never sees its own gold.
+- **Integration + reproduction:** [OntoLearner fork, PR #1](https://github.com/matias-vizcaino/OntoLearner-semanticswingers/pull/1) and the replication notebook
+  therein (`notebooks/pipeline_ontolearner.ipynb`), which runs Tasks A/B/C end-to-end.
+
+To reproduce: `learner = SemanticSwingersText2OntoLearner(train_mode="baseft",
+train_backend="mlx", output_dir=...)` then `learner.fit(train_docs, task="text2onto")`.
+
+## Intended use & limitations
+
+Research replication for the LLMs4OL 2026 shared task. Domain: general ontology construction from
+text; the training data is the challenge's Task A split. Not intended for production ontology
+engineering without validation. Inherits the base model's license and limitations.

adapter_config.json

@@ -0,0 +1,41 @@
+{
+    "adapter_path": "/Users/matias.vizcaino/Documents/datagero_repos/llms4ol-2026/data/ft/adapters_9b_full/seg_04",
+    "batch_size": 1,
+    "clear_cache_threshold": 1,
+    "config": null,
+    "data": "/Users/matias.vizcaino/Documents/datagero_repos/llms4ol-2026/data/ft/mlx35_nothink_full",
+    "fine_tune_type": "lora",
+    "grad_accumulation_steps": 4,
+    "grad_checkpoint": true,
+    "iters": 950,
+    "learning_rate": 7e-06,
+    "lora_parameters": {
+        "rank": 8,
+        "dropout": 0.0,
+        "scale": 20.0
+    },
+    "lr_schedule": null,
+    "mask_prompt": true,
+    "max_seq_length": 1024,
+    "model": "mlx-community/Qwen3.5-9B-4bit",
+    "num_layers": 8,
+    "optimizer": "adamw",
+    "optimizer_config": {
+        "adam": {},
+        "adamw": {},
+        "muon": {},
+        "sgd": {},
+        "adafactor": {}
+    },
+    "project_name": null,
+    "report_to": null,
+    "resume_adapter_file": "/Users/matias.vizcaino/Documents/datagero_repos/llms4ol-2026/data/ft/adapters_9b_full/seg_03/0000800_adapters.safetensors",
+    "save_every": 50,
+    "seed": 46,
+    "steps_per_eval": 400,
+    "steps_per_report": 25,
+    "test": false,
+    "test_batches": 500,
+    "train": true,
+    "val_batches": 10
+}

adapters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5835fd0711b95d40b39f35807d30af4d7976371aa6650ce87071de8be773bcae
+size 21654694