0.5.0

.gitattributes

@@ -35,9 +35,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 all-MiniLM-L6-v2.pte filter=lfs diff=lfs merge=lfs -text
 all-MiniLM-L6-v2_xnnpack.pte filter=lfs diff=lfs merge=lfs -text
-xnnpack/all_minilm_l6_v2_xnnpack_fp32.pte filter=lfs diff=lfs merge=lfs -text
-coreml/all_minilm_l6_v2_coreml_fp16.pte filter=lfs diff=lfs merge=lfs -text
-coreml/all_minilm_l6_v2_coreml_fp32.pte filter=lfs diff=lfs merge=lfs -text
-vulkan/all_minilm_l6_v2_vulkan_fp32.pte filter=lfs diff=lfs merge=lfs -text
-vulkan/all_minilm_l6_v2_vulkan_fp16.pte filter=lfs diff=lfs merge=lfs -text
-coreml/all_minilm_l6_v2_coreml_int8.pte filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,49 +1,22 @@
 ---
 license: apache-2.0
-pipeline_tag: sentence-similarity
-library_name: executorch
 ---
 
-# all-MiniLM-L6-v2
+# Introduction
 
-This repository hosts the **all-MiniLM-L6-v2** models exported for the
-[React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch)
-library as ExecuTorch `.pte` programs, ready to run on device.
+This repository hosts the [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/tree/main) models for the [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It includes the model exported for xnnpack in `.pte` format, ready for use in the **ExecuTorch** runtime.
 
-Upstream model: [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/tree/main)
+If you'd like to run these models in your own ExecuTorch runtime, refer to the [official documentation](https://pytorch.org/executorch/stable/index.html) for setup instructions.
 
-## Variants
-
-| Path | Backend | Precision |
-| --- | --- | --- |
-| `coreml/all_minilm_l6_v2_coreml_fp16.pte` | coreml | fp16 |
-| `vulkan/all_minilm_l6_v2_vulkan_fp16.pte` | vulkan | fp16 |
-| `xnnpack/all_minilm_l6_v2_xnnpack_fp32.pte` | xnnpack | fp32 |
-
-## Repository structure
+## Compatibility
 
-```
-config.json                                38 B
-coreml/all_minilm_l6_v2_coreml_fp16.pte    43.4 MB
-coreml/config.json                         929 B
-tokenizer.json                             695 kB
-tokenizer_config.json                      350 B
-vulkan/all_minilm_l6_v2_vulkan_fp16.pte    43.1 MB
-vulkan/config.json                         929 B
-xnnpack/all_minilm_l6_v2_xnnpack_fp32.pte  86.2 MB
-xnnpack/config.json                        931 B
-```
+If you intend to use this model outside of React Native ExecuTorch, make sure your runtime is compatible with the **ExecuTorch** version used to export the `.pte` files. For more details, see the compatibility note in the [ExecuTorch GitHub repository](https://github.com/pytorch/executorch/blob/11d1742fdeddcf05bc30a6cfac321d2a2e3b6768/runtime/COMPATIBILITY.md?plain=1#L4). If you work with React Native ExecuTorch, the constants from the library will  guarantee compatibility with runtime used behind the scenes.
 
-## Compatibility
+These models were exported using `v0.6.0` version and **no forward compatibility** is guaranteed. Older versions of the runtime may not work with these files.
 
-These files are published for the **ExecuTorch v1.4.1** runtime. ExecuTorch
-gives no forward compatibility guarantee, so an older runtime may fail to load
-them.
+### Repository Structure
 
-To use them in React Native ExecuTorch, pass the model constant shipped in the
-library's model registry to the corresponding task pipeline. See the
-[documentation](https://docs.swmansion.com/react-native-executorch/docs/fundamentals/downloading-models).
+All files are located in the root directory.
 
-To load these files in your own ExecuTorch runtime, read the
-[compatibility note](https://github.com/pytorch/executorch/blob/main/runtime/COMPATIBILITY.md)
-first.
+- The `.pte` file should be as the `modelSource` argument.
+- The tokenizer is provided as `tokenizer.json` in the root directory.

coreml/all_minilm_l6_v2_coreml_fp16.pte → all-MiniLM-L6-v2_xnnpack.pte

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c8da66ae5ba0e63169074d3ab845f030ae6f76df798f3338e269bc9575ddff
-size 45460244
+oid sha256:fda3d0dc0a8ea05065df154b91087cc6b6d03d8f1af85a037e13792a2be1654a
+size 90987520

config.json

@@ -1,3 +1,3 @@
 {
   "modelName": "all-MiniLM-L6-v2"
-}
+}

coreml/all_minilm_l6_v2_coreml_int8.pte

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f45794344ee2bc8eb991f125bb92ed4fdca1fdb1968601d68a8ff29d2b12da23
-size 22817740

coreml/config.json

@@ -1,83 +0,0 @@
-{
-  "$schema": "https://huggingface.co/software-mansion/react-native-executorch-spec/resolve/main/config.schema.json",
-  "model": "all_minilm_l6_v2",
-  "family": "sbert",
-  "capabilities": [
-    "text-embedding"
-  ],
-  "backend": "coreml",
-  "license": "apache-2.0",
-  "variants": [
-    {
-      "file": "all_minilm_l6_v2_coreml_int8.pte",
-      "precision": "int8",
-      "quantized": true,
-      "default": true,
-      "methods": {
-        "forward": {
-          "inputs": [
-            {
-              "shape": [
-                1,
-                254
-              ],
-              "dtype": "int64"
-            },
-            {
-              "shape": [
-                1,
-                254
-              ],
-              "dtype": "int64"
-            }
-          ],
-          "outputs": [
-            {
-              "shape": [
-                1,
-                384
-              ],
-              "dtype": "float32"
-            }
-          ]
-        }
-      },
-      "quantize": "int8"
-    },
-    {
-      "file": "all_minilm_l6_v2_coreml_fp16.pte",
-      "precision": "fp16",
-      "quantized": false,
-      "default": true,
-      "methods": {
-        "forward": {
-          "inputs": [
-            {
-              "shape": [
-                1,
-                254
-              ],
-              "dtype": "int64"
-            },
-            {
-              "shape": [
-                1,
-                254
-              ],
-              "dtype": "int64"
-            }
-          ],
-          "outputs": [
-            {
-              "shape": [
-                1,
-                384
-              ],
-              "dtype": "float32"
-            }
-          ]
-        }
-      }
-    }
-  ]
-}

vulkan/all_minilm_l6_v2_vulkan_fp16.pte

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8f9aed61f17b26a45551224ba06f6268431d476edbcc71abb43d4e70a22c23bf
-size 45208066

vulkan/config.json

@@ -1,45 +0,0 @@
-{
-  "$schema": "https://huggingface.co/software-mansion/react-native-executorch-spec/resolve/main/config.schema.json",
-  "model": "all_minilm_l6_v2",
-  "family": "sbert",
-  "capabilities": [
-    "text-embedding"
-  ],
-  "backend": "vulkan",
-  "license": "apache-2.0",
-  "variants": [
-    {
-      "file": "all_minilm_l6_v2_vulkan_fp16.pte",
-      "precision": "fp16",
-      "methods": {
-        "forward": {
-          "inputs": [
-            {
-              "shape": [
-                1,
-                254
-              ],
-              "dtype": "int64"
-            },
-            {
-              "shape": [
-                1,
-                254
-              ],
-              "dtype": "int64"
-            }
-          ],
-          "outputs": [
-            {
-              "shape": [
-                1,
-                384
-              ],
-              "dtype": "float32"
-            }
-          ]
-        }
-      }
-    }
-  ]
-}

xnnpack/all_minilm_l6_v2_xnnpack_fp32.pte

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3e59e86abfe09d5aa533fec095cef1f38cbdf21d9d5798996daea4d38a54dac7
-size 90391296

xnnpack/config.json

@@ -1,45 +0,0 @@
-{
-  "$schema": "https://huggingface.co/software-mansion/react-native-executorch-spec/resolve/main/config.schema.json",
-  "model": "all_minilm_l6_v2",
-  "family": "sbert",
-  "capabilities": [
-    "text-embedding"
-  ],
-  "backend": "xnnpack",
-  "license": "apache-2.0",
-  "variants": [
-    {
-      "file": "all_minilm_l6_v2_xnnpack_fp32.pte",
-      "precision": "fp32",
-      "methods": {
-        "forward": {
-          "inputs": [
-            {
-              "shape": [
-                1,
-                254
-              ],
-              "dtype": "int64"
-            },
-            {
-              "shape": [
-                1,
-                254
-              ],
-              "dtype": "int64"
-            }
-          ],
-          "outputs": [
-            {
-              "shape": [
-                1,
-                384
-              ],
-              "dtype": "float32"
-            }
-          ]
-        }
-      }
-    }
-  ]
-}