Update README.md

README.md

@@ -3,17 +3,19 @@ license: apache-2.0
 inference: false
 ---
 
-# SLIM-Q-GEN-PHI-3  
+# SLIM-Q-GEN-TINY  
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-**slim-q-gen-phi-3** implements a specialized function-calling question generation from a context passage, with output in the form of a python dictionary, e.g.,  
+**slim-q-gen-tiny** implements a specialized function-calling question generation from a context passage, with output in the form of a python dictionary, e.g.,  
 
 &nbsp;&nbsp;&nbsp;&nbsp;`{'question': ['What were earnings per share in the most recent quarter?'] }  
 
-This model is finetuned on top of phi-3-mini-4k-instruct base.  
+This model is finetuned on top of a tinyllama-1.1b base, and is intended for fast, local prototyping.  
 
-For fast inference use, we would recommend the 'quantized tool' version, e.g.,  [**'slim-q-gen-phi-3-tool'**](https://huggingface.co/llmware/slim-q-gen-phi-3-tool).  
+For fast inference use, we would recommend the 'quantized tool' version, e.g.,  [**slim-q-gen-tiny-tool**](https://huggingface.co/llmware/slim-q-gen-tiny-tool).  
+
+You also may want to checkout the finetuned phi-3 version of this model, e.g.,  [**slim-q-gen-phi-3-tool**](https://huggingface.co/llmware/slim-q-gen-phi-3-tool).  
 
 
 ## Prompt format:
@@ -27,8 +29,8 @@ For fast inference use, we would recommend the 'quantized tool' version, e.g.,
 <details>
 <summary>Transformers Script </summary>
 
-    model = AutoModelForCausalLM.from_pretrained("llmware/slim-q-gen-phi-3")
-    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-q-gen-phi-3")
+    model = AutoModelForCausalLM.from_pretrained("llmware/slim-q-gen-tiny")
+    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-q-gen-tiny")
 
     function = "generate"
     params = "boolean"
@@ -72,7 +74,7 @@ For fast inference use, we would recommend the 'quantized tool' version, e.g.,
 <summary>Using as Function Call in LLMWare</summary>
 
     from llmware.models import ModelCatalog
-    slim_model = ModelCatalog().load_model("llmware/slim-q-gen-phi-3", sample=True, temperature=0.7)  
+    slim_model = ModelCatalog().load_model("llmware/slim-q-gen-tiny", sample=True, temperature=0.7)  
     response = slim_model.function_call(text,params=["boolean"], function="generate")  
 
     print("llmware - llm_response: ", response)