Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

README.md

@@ -0,0 +1,48 @@
+---
+license: apache-2.0
+base_model: VTXAI/vtx-jev-mod-multilingual
+pipeline_tag: feature-extraction
+tags:
+- sentence-transformers
+- static-embeddings
+- model2vec
+- moderation
+- 100-languages
+- fast-inference
+- cpu-optimized
+---
+
+# VTX-MOD-1
+
+Ultra-fast **Static Embedding Model** distilled from [**VTXAI/vtx-jev-mod-multilingual**](https://huggingface.co/VTXAI/vtx-jev-mod-multilingual) with controlled 256 dimensions.
+
+Built using `model2vec` and `sentence-transformers` StaticEmbedding framework.
+
+### Specifications:
+- **Base Teacher**: `VTXAI/vtx-jev-mod-multilingual` (256,000 multilingual vocabulary)
+- **Output Dimensions**: 256 (Controlled via PCA + SIF weighting)
+- **Speed**: Up to 500x faster than standard transformers on CPU
+- **Coverage**: 100+ languages including Hindi, Bengali, Tamil, Telugu, Marathi, Urdu, Arabic, Chinese, Spanish, Russian, English.
+
+### Quick Usage:
+
+#### Using Sentence Transformers:
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("VTXAI/VTX-MOD-1")
+embeddings = model.encode([
+    "नमस्ते, क्या आप मेरी सहायता कर सकते हैं?",
+    "This is a safe sentence.",
+    "Very fast CPU inference!"
+])
+print(embeddings.shape) # (3, 256)
+```
+
+#### Using Model2Vec:
+```python
+from model2vec import StaticModel
+
+model = StaticModel.from_pretrained("VTXAI/VTX-MOD-1")
+embeddings = model.encode(["Hello world", "வணக்கம்"])
+```

config.json

@@ -0,0 +1,14 @@
+{
+    "model_type": "model2vec",
+    "architectures": [
+        "StaticModel"
+    ],
+    "tokenizer_name": "VTXAI/vtx-jev-mod-multilingual",
+    "apply_pca": 256,
+    "sif_coefficient": 0.0001,
+    "hidden_dim": 256,
+    "seq_length": 1000000,
+    "normalize": true,
+    "pooling": "mean",
+    "embedding_dtype": "float16"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d8907fe6ce29f77abc3522f693bdd87e42ac82c393b32474122a4092a88226
+size 130945624

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"
+    }
+]

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9936fce165782c51893821332063897271ba0e81b90b6a41548fcea48bf85e
+size 13598556