Add model

.gitattributes

@@ -33,3 +33,5 @@ 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
+model.sqlite filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,30 @@
+---
+tags:
+- sentence-similarity
+inference: false
+license: pddl
+language: en
+library_name: staticvectors
+---
+
+# GloVe 2024 WikiGiga StaticVectors model
+
+This model is an export of the new [GloVe 2024 WikiGiga Vectors](https://nlp.stanford.edu/projects/glove/) (_300d_) for [`staticvectors`](https://github.com/neuml/staticvectors). `staticvectors` enables running inference in Python with NumPy. This helps it maintain solid runtime performance.
+
+## Usage with StaticVectors
+
+```python
+from staticvectors import StaticVectors
+
+model = StaticVectors("neuml/glove-2024-wikigiga")
+model.embeddings(["word"])
+```
+
+Given that pre-trained embeddings models can get quite large, there is also a SQLite version that lazily loads vectors.
+
+```python
+from staticvectors import StaticVectors
+
+model = StaticVectors("neuml/glove-2024-wikigiga/model.sqlite")
+model.embeddings(["word"])
+```

config.json

@@ -0,0 +1,8 @@
+{
+  "model_type": "staticvectors",
+  "storage": "safetensors",
+  "format": "text",
+  "source": "wiki_giga_2024_300_MFT20_vectors_seed_2024_alpha_0.75_eta_0.05_combined.txt",
+  "total": 1200000,
+  "dim": 300
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee5f03734ac8206ee553740aa3e15b2f0dcf16787983eb83ac65a053696909e
+size 1549376488

model.sqlite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a2862a93b421bd5226ee434d923df8f66068f095989f3d03bb130009d1501e
+size 1791074304

vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614fd4f9a1dc2862bad8406806c241e005707226dfaac8f5a4c1f1a44bde3eeb
+size 25852205