chore(cargo): update for publishing

Author: LVivona

bintensors/Cargo.toml

@@ -3,16 +3,32 @@ name = "bintensors"
 version = "0.0.1-alpha.1"
 edition = "2024"
 license = "MIT"
+rust-version = "1.85"
 authors = ["Luca Vivona"]
 readme = "README.md"
+keywords = [
+    "bintensors",
+    "safetensors",
+    "Tensors",
+    "Pytorch",
+    "Numpy",
+    "bincode",
+]
 repository = "https://github.com/GnosisFoundation/bintensors"
 description = """
-Provides functions to read and write bintensors which aim to be faster then
-safetensors by using binary serialization rather then a JSON serialization.
-The format is 8 bytes which is an unsized int, being the size of a Binary header,
-the binary encoder header refers to the `dtype` the `shape` and `data_offsets` which are the offsets
-for the values in the rest of the file.
+bintensors is a high-performance binary tensor serialization 
+format designed to be faster than safetensors by eliminating 
+JSON metadata overhead. Instead of using JSON for metadata storage, 
+bintensors employs a compact binary header, reducing parsing time and improving I/O efficiency. 
+The format begins with an 8-byte unsigned integer (u64), indicating the size of the binary header. 
+This header contains essential tensor metadata, including the data type (dtype), 
+the shape of the tensor stored as a length-prefixed list, 
+and data offsets specifying where each tensor's raw values are stored within the file. 
+An index map is also included for named tensor lookups. With its efficient structure, 
+bintensors provides a fast and lightweight alternative for serializing and deserializing large models, 
+making it ideal for machine learning, scientific computing, and other high-performance applications.
 """
+exclude = ["target/*", "Cargo.lock"]
 
 [dependencies]
 bincode = { version = "2.0.1", default-features = false, features = ["derive"] }
@@ -27,7 +43,7 @@ sha2 = "0.10.8"
 sha1 = "0.10.6"
 
 
-[features]  
+[features]
 default = ["std"]
 std = ["bincode/default"]