Update README.md

README.md

@@ -7,22 +7,22 @@ inference: false
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-**slim-sentiment** is part of the SLIM ("**S**tructured **L**anguage **I**nstruction **M**odel") model series, consisting of small, specialized decoder-based models, fine-tuned for function-calling.  
+**slim-nli** is part of the SLIM ("**S**tructured **L**anguage **I**nstruction **M**odel") model series, consisting of small, specialized decoder-based models, fine-tuned for function-calling.  
 
-slim-sentiment has been fine-tuned for **sentiment analysis** function calls, generating output consisting of a python dictionary corresponding to specified keys, e.g.:  
+slim-sentiment has been fine-tuned for **natural language inference (nli)** function calls, generating output consisting of a python dictionary corresponding to specified keys, e.g.:  
 
-&nbsp;&nbsp;&nbsp;&nbsp;`{"sentiment": ["positive"]}`
+&nbsp;&nbsp;&nbsp;&nbsp;`{"evidence": ["contradicts"]}`
 
 
 SLIM models are designed to provide a flexible natural language generative model that can be used as part of a multi-step, multi-model LLM-based automation workflow.  
 
-Each slim model has a 'quantized tool' version, e.g.,  [**'slim-sentiment-tool'**](https://huggingface.co/llmware/slim-sentiment-tool).  
+Each slim model has a 'quantized tool' version, e.g.,  [**'slim-nli-tool'**](https://huggingface.co/llmware/slim-nli-tool).  
 
 
 ## Prompt format:
 
 `function = "classify"`  
-`params = "sentiment"`  
+`params = "nli"`  
 `prompt = "<human> " + {text} + "\n" + `  
 &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; &nbsp; &nbsp; &nbsp;`"<{function}> " + {params} + "</{function}>" + "\n<bot>:"`  
 
@@ -30,13 +30,20 @@ Each slim model has a 'quantized tool' version, e.g.,  [**'slim-sentiment-tool'*
 <details>
 <summary>Transformers Script </summary>
 
-    model = AutoModelForCausalLM.from_pretrained("llmware/slim-sentiment")
-    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-sentiment")
+    model = AutoModelForCausalLM.from_pretrained("llmware/slim-nli")
+    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-nli")
 
     function = "classify"
-    params = "sentiment"
+    params = "evidence"
 
-    text = "The stock market declined yesterday as investors worried increasingly about the slowing economy."  
+    # expects two statements - the first is evidence, and the second is a conclusion  
+    
+    text1 = "The stock market declined yesterday as investors worried increasingly about the slowing economy."  
+    text2 = "Investors are positive about the market."  
+
+    # the two statements are concatenated with optional/helpful "Evidence: " and "Conclusion: " added  
+    
+    text = "Evidence: " + text1 + "\n" + "Conclusion: " + text2  
     
     prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"