Upload adapter v1

README.md

@@ -0,0 +1,91 @@
+---
+base_model: fastino/gliner2.5-base-v1
+library_name: gliner2
+pipeline_tag: token-classification
+language:
+- en
+tags:
+- gliner2
+- lora
+- finance
+- options
+- ner
+---
+
+# options-recognizer-gliner2.5-base-v1
+
+LoRA adapter (v1) for [`fastino/gliner2.5-base-v1`](https://huggingface.co/fastino/gliner2.5-base-v1) (194M parameters) that extracts option-contract details from tweets: ticker, strike, option type, expiry, premium and price.
+
+Smaller bases are faster, larger ones are more accurate — see the sibling `options-recognizer-*` repos for the other sizes.
+
+## Results (exact-span match, held-out test set `9bbc0005d8a592af`)
+
+| label | precision | recall | F1 |
+|---|---|---|---|
+| ticker | 96.8% | 83.1% | 89.5% |
+| strike | 89.6% | 70.1% | 78.6% |
+| option_type | 100.0% | 95.6% | 97.7% |
+| expiry | 99.2% | 67.5% | 80.4% |
+| premium | 98.3% | 65.8% | 78.8% |
+| price | 93.4% | 85.2% | 89.1% |
+| overall | 96.5% | 78.9% | 86.8% |
+
+Inference: 10.49 ms/doc (batched, cuda).
+
+## Usage
+
+```python
+import json
+from gliner2 import GLiNER2
+from huggingface_hub import snapshot_download
+
+adapter_dir = snapshot_download("StephanAkkerman/options-recognizer-gliner2.5-base-v1")
+cfg = json.load(open(f"{adapter_dir}/recognizer_config.json"))
+model = GLiNER2.from_pretrained(cfg["base_model"])
+model.set_word_splitter(AlnumBoundarySplitter())  # required, see below
+model.load_adapter(adapter_dir)
+
+result = model.extract_entities(
+    "$AAPL 350 C 11/06/2026 $1.2M 4.37avg",
+    cfg["entity_descriptions"],
+    threshold=cfg["threshold"],
+)
+```
+
+Recommended threshold: **0.75**.
+
+## Required word splitter
+
+The adapter was trained with a custom word splitter that breaks between letters and digits, so `1.58avg` and `11/20exp` tokenize cleanly. Define it before loading the adapter, or accuracy drops sharply:
+
+```python
+import re
+
+class AlnumBoundarySplitter:
+    """GLiNER2 word splitter that also breaks between letters and digits.
+
+    The stock splitter keeps whole words together, so in ``1.58avg``, ``11/20exp``
+    and ``375C`` the gold span ends mid-word and can neither be trained on nor
+    predicted. Splitting at letter/digit boundaries makes those spans
+    word-aligned. Dates (``10/16/2026``) and numbers with decimals or thousands
+    separators (``5.1``, ``18,140``) stay whole so a fragment such as the ``10``
+    of a date can never be proposed as a strike. Must be used identically at
+    train and inference time.
+    """
+
+    _PATTERN = re.compile(
+        r"""(?:https?://[^\s]+|www\.[^\s]+)
+        |[a-z0-9._%+-]+@[a-z0-9.-]+\.[a-z]{2,}
+        |@[a-z0-9_]+
+        |[^\W\d_]+(?:[-_][^\W\d_]+)*
+        |\d{1,2}/\d{1,2}(?:/\d{2,4})?(?![\d,.]\d)
+        |\d+(?:[.,]\d+)*
+        |\S""",
+        re.VERBOSE | re.IGNORECASE,
+    )
+
+    def __call__(self, text, lower=True):
+        for m in self._PATTERN.finditer(text):
+            token = m.group()
+            yield (token.lower() if lower else token), m.start(), m.end()
+```

adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "BoundaryExtractor",
+    "parent_library": "gliner2.models.boundary.engine"
+  },
+  "base_model_name_or_path": "fastino/gliner2.5-base-v1",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_proj",
+    "value_proj",
+    "key_proj",
+    "dense"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa60f8984ec7857f3aae202be8fc5f0652c72e56802719851c4b7c1d1a9388d
+size 21254736

recognizer_config.json

@@ -0,0 +1,22 @@
+{
+  "base_model": "fastino/gliner2.5-base-v1",
+  "adapter_version": 1,
+  "labels": [
+    "ticker",
+    "strike",
+    "option_type",
+    "expiry",
+    "premium",
+    "price"
+  ],
+  "entity_descriptions": {
+    "ticker": "The stock or ETF symbol an option contract is written on, usually 1-5 letters and often preceded by a dollar sign (e.g., $AAPL, SPY, $T). MUST NOT be a company name, an @handle, or slang (YOLO, NFA, OTM, ITM).",
+    "strike": "The strike price of an option contract, e.g. 350, 162.5, or $1300 in '$1300 calls'. MUST NOT be the stock's current price, a premium or per-contract price, a date, or a percentage.",
+    "option_type": "Whether the contract is a call or a put, in any written form: C, P, call, calls, put, puts, c, p. Only the call/put word itself, not words like buyer or seller.",
+    "expiry": "The expiration date of an option contract: 10/16, 11/06/2026, 6/17/27, November 20, 2026, December, or relative like '2 days'. MUST NOT be the date a report was posted (e.g. the 10/2 in '10/2 Notable Flow').",
+    "premium": "The total dollar size of the trade, e.g. $1.2M, $993K, 23 million. MUST NOT be a strike, the per-contract price, or the stock price.",
+    "price": "The per-contract price or average fill, e.g. .15 in '@ .15' or 4.37 in '4.37avg'. Only the number. MUST NOT be a strike, premium, or the underlying's stock price."
+  },
+  "threshold": 0.75,
+  "word_splitter": "alnum-v2"
+}