Update README.md

README.md

@@ -3,21 +3,19 @@ license: apache-2.0
 inference: false  
 ---
 
-# dragon-phi-3-answer-tool
+# bling-phi-3
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-dragon-phi-3-answer-tool is part of the DRAGON ("Delivering RAG On ...") model series, RAG-instruct trained on top of a Microsoft Phi-3 base model.
-
-DRAGON models are fine-tuned with high-quality custom instruct datasets, designed for production use in RAG scenarios.
+bling-phi-3 is part of the BLING ("Best Little Instruct No-GPU") model series, RAG-instruct trained on top of a Microsoft Phi-3 base model.
 
 
 ### Benchmark Tests  
 
 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.  
+1 Test Run (temperature=0.0, sample=False) 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**:  **100.0** correct out of 100  
+--**Accuracy Score**:  **99.5** correct out of 100  
 --Not Found Classification:  95.0%  
 --Boolean:  97.5%  
 --Math/Logic:  80.0%  
@@ -32,7 +30,7 @@ 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:** Dragon 
+- **Model type:** bling
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
 - **Finetuned from model:** Microsoft Phi-3
@@ -71,14 +69,17 @@ Any model can provide inaccurate or incomplete information, and should be used i
 The fastest way to get started with BLING is through direct import in transformers:
 
     from transformers import AutoTokenizer, AutoModelForCausalLM  
-    tokenizer = AutoTokenizer.from_pretrained("bling-phi-2-v0", trust_remote_code=True)  
-    model = AutoModelForCausalLM.from_pretrained("bling-phi-2-v0", trust_remote_code=True)  
+    tokenizer = AutoTokenizer.from_pretrained("llmware/bling-phi-3", trust_remote_code=True)  
+    model = AutoModelForCausalLM.from_pretrained("llmware/bling-phi-3", 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.  
 
-The dRAGon model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
+The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
+
+    full_prompt = "<human>: " + my_prompt + "\n" + "<bot>:"  
+
+(As an aside, we intended to retire "human-bot" and tried several variations of the new Microsoft Phi-3 prompt template and ultimately had slightly better results with the very simple "human-bot" separators, so we opted to keep them.)  
 
-    full_prompt = "<human>: " + my_prompt + "\n" + "<bot>:"
 
 The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts: