Upload 5 files

README.md

@@ -0,0 +1,24 @@
+---
+library_name: model2vec
+license: mit
+model_name: cnmoro/custom-model2vec-tokenlearn-medium
+tags:
+- embeddings
+- static-embeddings
+- sentence-transformers
+---
+A custom model2vec model, trained using a modified version of the [tokenlearn](https://github.com/MinishLab/tokenlearn) library.
+
+The output dimension is 256, and the vocabulary size is 249.999
+
+The training process used a mix of English (10%) and Portuguese (90%) texts.
+
+```python
+from sentence_transformers import SentenceTransformer
+
+# Load a pretrained Sentence Transformer model
+model = SentenceTransformer("cnmoro/custom-model2vec-tokenlearn-medium")
+
+# Compute text embeddings
+embeddings = model.encode(["Example sentence"])
+```

config.json

@@ -0,0 +1,14 @@
+{
+    "model_type": "model2vec",
+    "architectures": [
+        "StaticModel"
+    ],
+    "tokenizer_name": "nomic-ai/nomic-embed-text-v2-moe",
+    "apply_pca": 256,
+    "sif_coefficient": 0.0001,
+    "hidden_dim": 256,
+    "seq_length": 1000000,
+    "normalize": true,
+    "pooling": "mean",
+    "embedding_dtype": "float32"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccec285a91720334f3f80e0a551c29dfca821d0dc3c6f75b4593da745eccd400
+size 255999064

modules.json

@@ -0,0 +1,14 @@
+[
+    {
+        "idx": 0,
+        "name": "0",
+        "path": ".",
+        "type": "sentence_transformers.models.StaticEmbedding"
+    },
+    {
+        "idx": 1,
+        "name": "1",
+        "path": "1_Normalize",
+        "type": "sentence_transformers.models.Normalize"
+    }
+]