Update README.md

README.md

@@ -6,9 +6,9 @@ license: apache-2.0
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-dragon-deci-7b-v0 is part of the dRAGon ("Delivering RAG On ...") model series, RAG-instruct trained on top of a DeciLM-7B base model.
+bling-phi-1_5b-v0 is part of the BLING ("Best Little Instruct No GPU required") model series, RAG-instruct trained on top of a Microsoft Phi-1.5B base model.
 
-DRAGON models are fine-tuned with high-quality custom instruct datasets, designed for production quality use in RAG scenarios.
+BLING models are fine-tuned with high-quality custom instruct datasets, designed for production quality use in RAG scenarios.
 
 
 ### Benchmark Tests  
@@ -16,12 +16,12 @@ DRAGON models are fine-tuned with high-quality custom instruct datasets, designe
 Evaluated against the benchmark test:   [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/rag_instruct_benchmark_tester)  
 Average of 2 Test Runs with 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations.  
 
---**Accuracy Score**:  **97.5** correct out of 100  
---Not Found Classification:  95.0%  
---Boolean:  92.5%  
---Math/Logic:  91.25%  
---Complex Questions (1-5):  4 (Medium-High: multiple choice, table reading, causal)  
---Summarization Quality (1-5):  4 (Coherent, extractive)  
+--**Accuracy Score**:  **87.75** correct out of 100  
+--Not Found Classification:  47.50%  
+--Boolean:  80.00%  
+--Math/Logic:  53,75%  
+--Complex Questions (1-5):  3 (Average-to-Low)  
+--Summarization Quality (1-5):  3 (Coherent, extractive)  
 --Hallucinations:  No hallucinations observed in test runs.  
 
 For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).
@@ -31,32 +31,30 @@ For test run results (and good indicator of target use cases), please see the fi
 <!-- Provide a longer summary of what this model is. -->
 
 - **Developed by:** llmware
-- **Model type:** DeciLM-7B
+- **Model type:** Phi-1.5B
 - **Language(s) (NLP):** English
-- **License:** Apache 2.0
-- **Finetuned from model:** DeciLM-7B-Base
+- **License:** Microsoft Research License (Non-Commercial)
+- **Finetuned from model:** Microsoft Phi-1.5B
 
 ## Uses
 
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
-The intended use of DRAGON models is two-fold:
+The intended use of BLING models is two-fold:
 
 1.  Provide high-quality RAG-Instruct models designed for fact-based, no "hallucination" question-answering in connection with an enterprise RAG workflow.
 
-2.  DRAGON models are fine-tuned on top of leading base foundation models, generally in the 6-7B+ range, and purposefully rolled-out across multiple base models to provide choices and "drop-in" replacements for RAG specific use cases.
-
-3.  DRAGON models were trained on the same principles as the BLING models, so generally, it should be easy to "upgrade" from a BLING model in testing to a DRAGON model in production.
+2.  BLING models are fine-tuned on top of leading base foundation models, generally in the 1-3B+ range, and purposefully rolled-out across multiple base models to provide choices and "drop-in" replacements for RAG specific use cases.
 
 
 ### Direct Use
 
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-DRAGON is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services,
+BLING is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services,
 legal and regulatory industries with complex information sources.  
 
-DRAGON models have been trained for common RAG scenarios, specifically:   question-answering, key-value extraction, and basic summarization as the core instruction types
+BLING models have been trained for common RAG scenarios, specifically:   question-answering, key-value extraction, and basic summarization as the core instruction types
 without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
 
 
@@ -72,8 +70,8 @@ Any model can provide inaccurate or incomplete information, and should be used i
 The fastest way to get started with dRAGon is through direct import in transformers:
 
     from transformers import AutoTokenizer, AutoModelForCausalLM  
-    tokenizer = AutoTokenizer.from_pretrained("dragon-deci-7b-v0", trust_remote_code=True)  
-    model = AutoModelForCausalLM.from_pretrained("dragon-deci-7b-v0", trust_remote_code=True)  
+    tokenizer = AutoTokenizer.from_pretrained("bling-phi-1_5b-v0", trust_remote_code=True)  
+    model = AutoModelForCausalLM.from_pretrained("bling-phi-1_5b-v0", trust_remote_code=True)  
 
 Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model.  The **generation_test_llmware_script.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.