Update README.md

README.md

@@ -1,59 +1,37 @@
 ---
-license: other
-license_link: https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE  
-license_name: yi-license
-model_creator: 01-ai  
-model_name:  Yi 6B  
-model_type:  yi
+license: apache-2.0
 ---
 
 # Model Card for Model ID
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-dragon-yi-6b-v0 part of the dRAGon ("Delivering RAG On ...") model series, RAG-instruct trained on top of a Yi-6B 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.
-
+slim-sql-1b-v0 is part of the slim model series.
 
 ### 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.  
+Evaluated against 100 test SQL queries with under 100 characters. 1 point given for exact string match, 0 given for incorrect answer.  
 
---**Accuracy Score**:  **99.5** correct out of 100  
---Not Found Classification:  90.0%  
---Boolean:  87.5%  
---Math/Logic:  77.5%  
---Complex Questions (1-5):  4 (Above Average)  
---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).
+--**Accuracy Score**:  **86** correct out of 100 
+- 8 incorrect answers attributed to query structure ordering or naming convention differences
+- 6 incorrect answers attributed to incorrect variable selection or aggregate function use
 
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->
 
 - **Developed by:** llmware
-- **Model type:** Yi
+- **Model type:** TinyLlama
 - **Language(s) (NLP):** English
-- **License:** Yi License [Link](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE)
-- **Finetuned from model:** Yi-6B
+- **License:** apache-2.0
+- **Finetuned from model:** [TinyLlama-1.1b - 2.5T checkpoint](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T)
 
 
 ### 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,
-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
-without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
-
-This model is licensed according to the terms of the license of the base model, Yi-6B, at this [link](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE).
-
+slim is designed for... 
 
 ## Bias, Risks, and Limitations
 
@@ -64,27 +42,27 @@ Any model can provide inaccurate or incomplete information, and should be used i
 
 ## How to Get Started with the Model
 
-The fastest way to get started with BLING is through direct import in transformers:
+The fastest way to get started with slim is through direct import in transformers:
 
     from transformers import AutoTokenizer, AutoModelForCausalLM  
-    tokenizer = AutoTokenizer.from_pretrained("dragon-yi-6b-v0")  
-    model = AutoModelForCausalLM.from_pretrained("dragon-yi-6b-v0")  
+    tokenizer = AutoTokenizer.from_pretrained("slim-sql-1b-v0")  
+    model = AutoModelForCausalLM.from_pretrained("slim-sql-1b-v0")  
 
-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.  
+Please refer to the generation_test.py files in the Files repository, which includes 100 samples and script to test the model. 
 
-The DRAGON model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
+The sql-slim 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>:"
 
-The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts:
+The prompt consists of two sub-parts:
 
-1.  Text Passage Context, and
+1.  Table creation prompt providing table name, variables, and variable type.
 2.  Specific question or instruction based on the text passage
 
-To get the best results, package "my_prompt" as follows:
-
-    my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
+Training sample example: "text": "<human>: CREATE TABLE table_name_8 ( partner VARCHAR, date VARCHAR )\nName the partner for may 2, 1993\n<bot>:SELECT partner FROM table_name_8 WHERE date = \"may 2, 1993\"</s>"}
+{"text": "<human>: CREATE TABLE table_name_97 ( Id VARCHAR )\nName the 2012 when 2011 is qf\n<bot>:SELECT 2012 FROM table_name_97 WHERE 2011 = \"qf\"</s>"
 
+Test samples are provided in this repo ("sql-slim-1b_test_questions")
 
 If you are using a HuggingFace generation script:
 
@@ -111,4 +89,4 @@ If you are using a HuggingFace generation script:
 
 ## Model Card Contact
 
-Darren Oberst & llmware team
+Dylan Oberst & llmware team