Duplicate from urchade/gliner_large_bio-v0.1

Co-authored-by: Urchade Zaratiana <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,16 @@
+---
+license: apache-2.0
+pipeline_tag: token-classification
+tags:
+- biology
+- medical
+language:
+- en
+library_name: gliner
+datasets:
+- urchade/pubmed-ner-mistral-v0.1
+---
+
+This version is trained with "urchade/pubmed-ner-mistral-v0.1" which is commercially permissible.
+
+This version can work for many domains, but better than other GLiNER models in the biomedical domain. Use with threshold=0.3 for better performance.

gliner_config.json

@@ -0,0 +1,22 @@
+{
+  "size_sup": -1,
+  "max_types": 25,
+  "shuffle_types": true,
+  "random_drop": true,
+  "max_neg_type_ratio": 1,
+  "max_len": 300,
+  "lr_encoder": "1e-5",
+  "lr_others": "5e-5",
+  "num_steps": 30000,
+  "warmup_ratio": 3000,
+  "train_batch_size": 8,
+  "eval_every": 5000,
+  "max_width": 12,
+  "model_name": "microsoft/deberta-v3-large",
+  "fine_tune": true,
+  "subtoken_pooling": "first",
+  "hidden_size": 512,
+  "span_mode": "markerV0",
+  "dropout": 0.4,
+  "name": "correct"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d02a80b241b8ec990e754ab7c6efaaf05c66dc4ffd18f5cf3badb5e262601f4
+size 1782044554