fix: fix model sizes in supported models lists

qdrant · Mar 29, 2024 · 23966ec · 23966ec
1 parent 62c21b0
commit 23966ec
Show file tree

Hide file tree

Showing 3 changed files with 23 additions and 15 deletions.
diff --git a/fastembed/text/e5_onnx_embedding.py b/fastembed/text/e5_onnx_embedding.py
@@ -20,7 +20,7 @@
         "model": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
         "dim": 768,
         "description": "Sentence-transformers model for tasks like clustering or semantic search",
-        "size_in_GB": 1.11,
+        "size_in_GB": 1.00,
         "sources": {
             "hf": "xenova/paraphrase-multilingual-mpnet-base-v2",
         },

diff --git a/fastembed/text/jina_onnx_embedding.py b/fastembed/text/jina_onnx_embedding.py
@@ -11,14 +11,14 @@
         "model": "jinaai/jina-embeddings-v2-base-en",
         "dim": 768,
         "description": "English embedding model supporting 8192 sequence length",
-        "size_in_GB": 0.55,
+        "size_in_GB": 0.52,
         "sources": {"hf": "xenova/jina-embeddings-v2-base-en"},
     },
     {
         "model": "jinaai/jina-embeddings-v2-small-en",
         "dim": 512,
         "description": "English embedding model supporting 8192 sequence length",
-        "size_in_GB": 0.13,
+        "size_in_GB": 0.12,
         "sources": {"hf": "xenova/jina-embeddings-v2-small-en"},
     },
 ]

diff --git a/fastembed/text/onnx_embedding.py b/fastembed/text/onnx_embedding.py
@@ -12,7 +12,7 @@
         "model": "BAAI/bge-base-en",
         "dim": 768,
         "description": "Base English model",
-        "size_in_GB": 0.5,
+        "size_in_GB": 0.42,
         "sources": {
             "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz",
         },
@@ -21,7 +21,7 @@
         "model": "BAAI/bge-base-en-v1.5",
         "dim": 768,
         "description": "Base English model, v1.5",
-        "size_in_GB": 0.44,
+        "size_in_GB": 0.21,
         "sources": {
             "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz",
             "hf": "qdrant/bge-base-en-v1.5-onnx-q",
@@ -31,7 +31,7 @@
         "model": "BAAI/bge-large-en-v1.5-quantized",
         "dim": 1024,
         "description": "Large English model, v1.5",
-        "size_in_GB": 1.34,
+        "size_in_GB": 0.64,
         "sources": {
             "hf": "qdrant/bge-large-en-v1.5-onnx-q",
         },
@@ -40,7 +40,7 @@
         "model": "BAAI/bge-large-en-v1.5",
         "dim": 1024,
         "description": "Large English model, v1.5",
-        "size_in_GB": 1.34,
+        "size_in_GB": 1.20,
         "sources": {
             "hf": "qdrant/bge-large-en-v1.5-onnx",
         },
@@ -49,7 +49,7 @@
         "model": "BAAI/bge-small-en",
         "dim": 384,
         "description": "Fast English model",
-        "size_in_GB": 0.2,
+        "size_in_GB": 0.13,
         "sources": {
             "url": "https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz",
         },
@@ -72,19 +72,27 @@
         "size_in_GB": 0.13,
         "sources": {
             "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en-v1.5.tar.gz",
+        },
+    },
+    {
+        "model": "BAAI/bge-small-en-v1.5-quantized",
+        "dim": 384,
+        "description": "Fast and Default English model",
+        "size_in_GB": 0.06,
+        "sources": {
             "hf": "qdrant/bge-small-en-v1.5-onnx-q",
         },
     },
     {
         "model": "BAAI/bge-small-zh-v1.5",
         "dim": 512,
         "description": "Fast and recommended Chinese model",
-        "size_in_GB": 0.1,
+        "size_in_GB": 0.09,
         "sources": {
             "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz",
         },
     },
-    {  # todo: it is not a flag embedding
+    {
         "model": "sentence-transformers/all-MiniLM-L6-v2",
         "dim": 384,
         "description": "Sentence Transformer model, MiniLM-L6-v2",
@@ -98,7 +106,7 @@
         "model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
         "dim": 384,
         "description": "Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2",
-        "size_in_GB": 0.46,
+        "size_in_GB": 0.22,
         "sources": {
             "hf": "qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q",
         },
@@ -107,7 +115,7 @@
         "model": "nomic-ai/nomic-embed-text-v1",
         "dim": 768,
         "description": "8192 context length english model",
-        "size_in_GB": 0.54,
+        "size_in_GB": 0.52,
         "sources": {
             "hf": "nomic-ai/nomic-embed-text-v1",
         },
@@ -116,7 +124,7 @@
         "model": "nomic-ai/nomic-embed-text-v1.5",
         "dim": 768,
         "description": "8192 context length english model",
-        "size_in_GB": 0.54,
+        "size_in_GB": 0.52,
         "sources": {
             "hf": "nomic-ai/nomic-embed-text-v1.5",
         },
@@ -125,7 +133,7 @@
         "model": "thenlper/gte-large",
         "dim": 1024,
         "description": "Large general text embeddings model",
-        "size_in_GB": 1.34,
+        "size_in_GB": 1.20,
         "sources": {
             "hf": "qdrant/gte-large-onnx",
         },
@@ -147,7 +155,7 @@
     "model": "mixedbread-ai/mxbai-embed-large-v1",
     "dim": 1024,
     "description": "MixedBread Base sentence embedding model, does well on MTEB",
-    "size_in_GB": 1.34, 
+    "size_in_GB": 0.64,
     "sources": {
         "hf": "mixedbread-ai/mxbai-embed-large-v1",
         },