Merge pull request #709 from Teradata/bugfix_small_lang_model

updated command to d/l model and updated links to notebook

UseCases/Language_Models_InVantage/Initialization_and_Model_Load.ipynb

@@ -193,11 +193,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a2eaca1b-1a48-43fc-b072-4f3ed946207b",
+   "id": "519fafdd-099f-4b6f-902d-8fb9034bf372",
    "metadata": {},
    "outputs": [],
    "source": [
-    "!optimum-cli export onnx --opset 16 --trust-remote-code -m BAAI/bge-small-en-v1.5 bge-small-en-v1.5-onnx"
+    "!optimum-cli export onnx --opset 16 --trust-remote-code --task sentence-similarity -m BAAI/bge-small-en-v1.5 bge-small-en-v1.5-onnx"
    ]
   },
   {
@@ -373,9 +373,9 @@
     "<p style = 'font-size:16px;font-family:Arial;color:#00233C'> Now we have initialized and loaded the model into Vantage.  Now the notebooks listed below can be executed.\n",
     "<ul style = 'font-size:16px;font-family:Arial;color:#00233C'> \n",
     "       <li>Semantic Similarity:Does Embeddings on CFPB complaints and uses TD_VECTORDISTANCE to find complaints that match some theme or topic <a href = './Semantic_Similarity_Python.ipynb'>Semantic Similarity </a></li> \n",
-    "     <li>Semantic Clustering:Does Embeddings on CFPB complaints and uses K-MEANS to cluster and does Post-hoc explanations/topic detection on semantic clusters found. <a href = './SemanticClustering.ipynb '>Semantic Clustering </a></li> \n",
-    "     <li>RAG Notebook for TD Catalog:Does a dump of TD Catalog Metadata on a table. Does embeddings on both Metadata + LLM prompt query. Does Semantic Similarity search of Top N Chunks and hands it off to a LLM to answer the prompt.<a href = './RAG_and_LLM_Querycatalogue.ipynb'>RAG and LLM to query Catalogue </a></li> \n",
-    "     <li>RAG Notebook for SEC-10K PDF:Demo with some PDF parsing and chunking with a Teradata SEC-10K PDF, creates embedding and uses LLM to answer prompts <a href = './RAG_and_LLM_QueryPDF.ipynb'>RAG and LLM to query Pdf </a></li> \n",
+    "     <li>Semantic Clustering:Does Embeddings on CFPB complaints and uses K-MEANS to cluster and does Post-hoc explanations/topic detection on semantic clusters found. <a href = './Semantic_Clustering_Python.ipynb'>Semantic Clustering </a></li> \n",
+    "     <li>RAG Notebook for TD Catalog:Does a dump of TD Catalog Metadata on a table. Does embeddings on both Metadata + language model prompt query. Does Semantic Similarity search of Top N Chunks and hands it off to a LLM to answer the prompt.<a href = './RAG_and_Bedrock_Querycatalogue.ipynb'>RAG and Bedrock to query Catalogue </a></li> \n",
+    "     <li>RAG Notebook for SEC-10K PDF:Demo with some PDF parsing and chunking with a Teradata SEC-10K PDF, creates embedding and uses language model to answer prompts <a href = './RAG_and_Bedrock_QueryPDF.ipynb'>RAG and Bedrock to query Pdf </a></li> \n",
     "      \n",
     "</ul>\n",
     "    </p>"