Update README.md

README.md

@@ -11,9 +11,7 @@ inference: false
 
 slim-sentiment has been fine-tuned for **sentiment analysis** function calls, generating output consisting of a python dictionary corresponding to specified keys.  
 
-Each slim model has a corresponding 'tool' in a separate repository, e.g.,  
-
-[**'slim-sentiment-tool'**](https://huggingface.co/llmware/slim-sentiment-tool), which a 4-bit quantized gguf version of the model that is intended to be used for inference.  
+Each slim model has a corresponding 'tool' in a separate repository, e.g.,  [**'slim-sentiment-tool'**](https://huggingface.co/llmware/slim-sentiment-tool), which a 4-bit quantized gguf version of the model that is intended to be used for inference.  
 
 Inference speed and loading time is much faster with the 'tool' versions of the model, and multiple tools can be deployed concurrently and run on a local CPU-based laptop or server.   
 
@@ -33,8 +31,16 @@ Inference speed and loading time is much faster with the 'tool' versions of the
 
 The intended use of SLIM models is to re-imagine traditional 'hard-coded' classifiers through the use of function calls, and to provide a natural language flexible tool that can be used as decision gates and processing steps in a complex LLM-based automation workflow.  
 
+## Prompt format:
+
+    "<human> " + {text} + "\n" +
+    
+    "<{function}> " + {keys} + "</{function}>" + 
+    
+    "/n<bot>:"  
+    
 <details>
-<summary><b>Getting Started: </b> </summary>
+<summary><b>Getting Started Example: </b> </summary>
 
     model = AutoModelForCausalLM.from_pretrained("llmware/slim-sentiment")
     tokenizer = AutoTokenizer.from_pretrained("llmware/slim-sentiment")
@@ -60,36 +66,21 @@ The intended use of SLIM models is to re-imagine traditional 'hard-coded' classi
 
     output_only = tokenizer.decode(outputs[0][start_of_input:], skip_special_tokens=True)
 
-    print("output only: ", output_only)
-</details>
-
-Sample output:
-
-    {"sentiment": ["negative"]}
-
-
-## Prompt Instruction format: all of the SLIM models use a novel prompt instruction structured as follows:
-
-    "<human> " + {text} + "\n" +
-    
-    "<{function}> " + {keys} + "</{function}>" + 
-    
-    "/n<bot>:"
-
-For example, in this case, the prompt would be as follows:  
-
-    "<human>" + "The stock market declined yesterday ..." + "\n" + "<classify> sentiment </classify>" + "\n<bot>:"  
-
-The model generation output will be a string in the form of a python dictionary, which can be converted as follows:
+    print("output only: ", output_only)  
 
+    # here's the fun part
     try:
         output_only = ast.literal_eval(llm_string_output)
         print("success - converted to python dictionary automatically")
-
     except:
         print("fail - could not convert to python dictionary automatically - ", llm_string_output)
 
-   
+    # sample output
+        {"sentiment": ["negative"]}  
+        
+   </details>
+
+
 ## Using as Function Call in LLMWare
 
 We envision the slim models deployed in a pipeline/workflow/templating framework that handles the prompt packaging more elegantly.