Update README.md

README.md

@@ -15,6 +15,13 @@ slim-sa-ner-3b combines two of the most popular traditional classifier functions
 
 This 'combo' model is designed to illustrate the potential power of using function calls on small, specialized models to enable a single model architecture to combine the capabilities of what were traditionally two separate model architectures on an encoder.  
 
+The intent of SLIMs is to forge a middle-ground between traditional encoder-based classifiers and open-ended API-based LLMs.  
+
+**Compared to encoder classifiers**:  provide intuitive natural language responses that fit more naturally in LLM-based agent processes, generalize better, provide a better fine-tuning base for specialized domains, and offer the potential for combining different classification modalities into a single model architecture.  
+
+**Compared to API-based Mega language models**:  small, specialized, do a few things well, run locally, and do not require complex prompt instructions to generate syntactically correct format and keys.  
+
+
 This model is fine-tuned on top of [**llmware/bling-stable-lm-3b-4e1t-v0**](https://huggingface.co/llmware/bling-stable-lm-3b-4e1t-v0), which in turn, is a fine-tune of stabilityai/stablelm-3b-4elt.
 
 Each slim model has a 'quantized tool' version, e.g.,  [**'slim-sa-ner-3b-tool'**](https://huggingface.co/llmware/slim-sa-ner-3b-tool).