Merge pull request #3 from philipithomas/philipithomas/maintenance

Maintenance: Browser compatibility, docs updates

Author: philipithomas

.github/workflows/documentation.yml

@@ -10,3 +10,4 @@ node_modules
 
 # Do not track coverage reports
 /coverage
+.npmrc

.github/workflows/gh-pages.yml

@@ -2,7 +2,7 @@
 
 <p align="center">
     <br/>
-    <picture> 
+    <picture>
         <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/datasets/Xenova/transformers.js-docs/raw/main/transformersjs-dark.svg" width="500" style="max-width: 100%;">
         <source media="(prefers-color-scheme: light)" srcset="https://huggingface.co/datasets/Xenova/transformers.js-docs/raw/main/transformersjs-light.svg" width="500" style="max-width: 100%;">
         <img alt="transformers.js javascript library logo" src="https://huggingface.co/datasets/Xenova/transformers.js-docs/raw/main/transformersjs-light.svg" width="500" style="max-width: 100%;">
@@ -11,14 +11,14 @@
 </p>
 
 <p align="center">
-    <a href="https://www.npmjs.com/package/@xenova/transformers">
-        <img alt="NPM" src="https://img.shields.io/npm/v/@xenova/transformers">
+    <a href="https://www.npmjs.com/package/chromadb-default-embed">
+        <img alt="NPM" src="https://img.shields.io/npm/v/chromadb-default-embed">
     </a>
-    <a href="https://www.npmjs.com/package/@xenova/transformers">
-        <img alt="NPM Downloads" src="https://img.shields.io/npm/dw/@xenova/transformers">
+    <a href="https://www.npmjs.com/package/chromadb-default-embed">
+        <img alt="NPM Downloads" src="https://img.shields.io/npm/dw/chromadb-default-embed">
     </a>
-    <a href="https://www.jsdelivr.com/package/npm/@xenova/transformers">
-        <img alt="jsDelivr Hits" src="https://img.shields.io/jsdelivr/npm/hw/@xenova/transformers">
+    <a href="https://www.jsdelivr.com/package/npm/chromadb-default-embed">
+        <img alt="jsDelivr Hits" src="https://img.shields.io/jsdelivr/npm/hw/chromadb-default-embed">
     </a>
     <a href="https://github.com/xenova/transformers.js/blob/main/LICENSE">
         <img alt="License" src="https://img.shields.io/github/license/xenova/transformers.js?color=blue">
@@ -38,7 +38,7 @@ Transformers.js is designed to be functionally equivalent to Hugging Face's [tra
   - 🗣️ **Audio**: automatic speech recognition and audio classification.
   - 🐙 **Multimodal**: zero-shot image classification.
 
-Transformers.js uses [ONNX Runtime](https://onnxruntime.ai/) to run models in the browser. The best part about it, is that you can easily [convert](#convert-your-models-to-onnx) your pretrained PyTorch, TensorFlow, or JAX models to ONNX using [🤗 Optimum](https://github.com/huggingface/optimum#onnx--onnx-runtime). 
+Transformers.js uses [ONNX Runtime](https://onnxruntime.ai/) to run models in the browser. The best part about it, is that you can easily [convert](#convert-your-models-to-onnx) your pretrained PyTorch, TensorFlow, or JAX models to ONNX using [🤗 Optimum](https://github.com/huggingface/optimum#onnx--onnx-runtime).
 
 For more information, check out the full [documentation](https://huggingface.co/docs/transformers.js).
 
@@ -70,7 +70,7 @@ out = pipe('I love transformers!')
 <td>
 
 ```javascript
-import { pipeline } from '@xenova/transformers';
+import { pipeline } from 'chromadb-default-embed';
 
 // Allocate a pipeline for sentiment-analysis
 let pipe = await pipeline('sentiment-analysis');
@@ -94,15 +94,15 @@ let pipe = await pipeline('sentiment-analysis', 'Xenova/bert-base-multilingual-u
 ## Installation
 
 
-To install via [NPM](https://www.npmjs.com/package/@xenova/transformers), run:
+To install via [NPM](https://www.npmjs.com/package/chromadb-default-embed), run:
 ```bash
-npm i @xenova/transformers
+npm i chromadb-default-embed
 ```
 
 Alternatively, you can use it in vanilla JS, without any bundler, by using a CDN or static hosting. For example, using [ES Modules](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Modules), you can import the library with:
 ```html
 <script type="module">
-    import { pipeline } from 'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.13.2';
+    import { pipeline } from 'https://cdn.jsdelivr.net/npm/chromadb-default-embed@2.13.2';
 </script>
 ```
 
@@ -135,13 +135,13 @@ Check out the Transformers.js [template](https://huggingface.co/new-space?templa
 
 
 
-By default, Transformers.js uses [hosted pretrained models](https://huggingface.co/models?library=transformers.js) and [precompiled WASM binaries](https://cdn.jsdelivr.net/npm/@xenova/transformers@2.13.2/dist/), which should work out-of-the-box. You can customize this as follows:
+By default, Transformers.js uses [hosted pretrained models](https://huggingface.co/models?library=transformers.js) and [precompiled WASM binaries](https://cdn.jsdelivr.net/npm/chromadb-default-embed@2.13.2/dist/), which should work out-of-the-box. You can customize this as follows:
 
 
 ### Settings
 
 ```javascript
-import { env } from '@xenova/transformers';
+import { env } from 'chromadb-default-embed';
 
 // Specify a custom location for models (defaults to '/models/').
 env.localModelPath = '/path/to/models/';

.gitignore

@@ -1,6 +1,6 @@
 {
   "name": "chromadb-default-embed",
-  "version": "2.13.3",
+  "version": "2.14.0",
   "description": "Chroma's fork of @xenova/transformers serving as our default embedding function",
   "main": "./src/transformers.js",
   "types": "./types/transformers.d.ts",

README.md

@@ -162,15 +162,15 @@
         # Token classification
         'token-classification': [
             'Jean-Baptiste/camembert-ner',
-            'Jean-Baptiste/camembert-ner-with-dates',
+            # 'Jean-Baptiste/camembert-ner-with-dates',
             'pythainlp/thainer-corpus-v2-base-model',
-            'gilf/french-camembert-postag-model',
+            # 'gilf/french-camembert-postag-model',
         ],
 
         # Masked language modelling
         'fill-mask': [
             'camembert-base',
-            'airesearch/wangchanberta-base-att-spm-uncased',
+            # 'airesearch/wangchanberta-base-att-spm-uncased',
         ],
     },
     'clap': {
@@ -387,13 +387,13 @@
     'donut': {  # NOTE: also a `vision-encoder-decoder`
         # Image-to-text
         'image-to-text': [
-            'naver-clova-ix/donut-base-finetuned-cord-v2',
-            'naver-clova-ix/donut-base-finetuned-zhtrainticket',
+            #'naver-clova-ix/donut-base-finetuned-cord-v2',
+            #'naver-clova-ix/donut-base-finetuned-zhtrainticket',
         ],
 
         # Document Question Answering
         'document-question-answering': [
-            'naver-clova-ix/donut-base-finetuned-docvqa',
+            # 'naver-clova-ix/donut-base-finetuned-docvqa',
         ],
     },
     'dpt': {
@@ -575,9 +575,9 @@
     'mbart': {
         # Translation
         'translation': [
-            'facebook/mbart-large-50-many-to-many-mmt',
-            'facebook/mbart-large-50-many-to-one-mmt',
-            'facebook/mbart-large-50',
+            # 'facebook/mbart-large-50-many-to-many-mmt',
+            #'facebook/mbart-large-50-many-to-one-mmt',
+            # 'facebook/mbart-large-50',
         ],
     },
     'mistral': {
@@ -632,7 +632,7 @@
         # Text-to-text
         'text2text-generation': [
             'google/mt5-small',
-            'google/mt5-base',
+            # 'google/mt5-base',
         ],
     },
     'nougat': {
@@ -835,8 +835,8 @@
         ('translation', 'summarization'): [
             't5-small',
             't5-base',
-            'google/t5-v1_1-small',
-            'google/t5-v1_1-base',
+            # 'google/t5-v1_1-small',
+            # 'google/t5-v1_1-base',
             'google/flan-t5-small',
             'google/flan-t5-base',
         ],
@@ -873,7 +873,7 @@
     'trocr': {  # NOTE: also a `vision-encoder-decoder`
         # Text-to-image
         'text-to-image': [
-            'microsoft/trocr-small-printed',
+            # 'microsoft/trocr-small-printed',
             'microsoft/trocr-base-printed',
             'microsoft/trocr-small-handwritten',
             'microsoft/trocr-base-handwritten',