Update README.md

README.md

@@ -1,39 +1,46 @@
 ---
-license: llama2
+license: apache-2.0  
+inference: false 
 ---
 
-# Model Card for Model ID
+# DRAGON-MISTRAL-0.3
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-dragon-llama-7b-v0 part of the dRAGon ("Delivering RAG On ...") model series, RAG-instruct trained on top of a LLama-2 base model.
+dragon-mistral-0.3 is part of the dRAGon ("Delivering RAG On ...") model series, RAG-instruct trained on top of a Mistral 7b (0.3) base model.
 
 DRAGON models have been fine-tuned with the specific objective of fact-based question-answering over complex business and legal documents with an emphasis on reducing hallucinations and providing short, clear answers for workflow automation.
 
+
 ### 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.  
-
---**Accuracy Score**:  **97.25** correct out of 100  
---Not Found Classification:  92.50%  
---Boolean:  95.00%  
---Math/Logic:  63.75%  
---Complex Questions (1-5):  3 (Medium)  
---Summarization Quality (1-5):  3 (Coherent, extractive)  
+1 Test Run (with temperature = 0.0 and 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**:  **99.5** correct out of 100  
+--Not Found Classification:  95.0%  
+--Boolean:  82.5%  
+--Math/Logic:  67.5%  
+--Complex Questions (1-5):  4 (Above Average - multiple-choice, causal)  
+--Summarization Quality (1-5):  4 (Above Average)  
 --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).
+For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).  
+
+Please note that these test results were achieved using the 4_K_M quantized version of this model - [dragon-mistral-0.3-gguf](https://wwww.huggingface.co/llmware/dragon-mistral-0.3-gguf).  
+
+Note: compare results with [dragon-mistral-7b](https://www.huggingface.co/llmware/dragon-mistral-7b-v0).  
+
 
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->
 
 - **Developed by:** llmware
-- **Model type:** LLama-2 
+- **Model type:** mistral 
 - **Language(s) (NLP):** English
-- **License:** LLama 2 Community License Agreement
-- **Finetuned from model:** Llama-2-7B-Base
+- **License:** Apache 2.0
+- **Finetuned from model:** Mistral-7b-base-0.3
 
 
 ### Direct Use
@@ -59,8 +66,8 @@ 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-llama-7b-v0")  
-    model = AutoModelForCausalLM.from_pretrained("dragon-llama-7b-v0")  
+    tokenizer = AutoTokenizer.from_pretrained("dragon-mistral-0.3")  
+    model = AutoModelForCausalLM.from_pretrained("dragon-mistral-0.3")  
 
 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.