Update README.md

README.md

@@ -1,25 +1,25 @@
 ---
-license: cc-by-sa-4.0
+license: apache-2.0
 inference: false
 ---
 
-# SLIM-EXTRACT
+# SLIM-Q-GEN-PHI-3  
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-**slim-extract** implements a specialized function-calling customizable 'extract' capability that takes as an input a context passage, a customized key, and outputs a python dictionary with key that corresponds to the customized key, with a value consisting of a list of items extracted from the text corresponding to that key, e.g., 
+**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.,  
 
-&nbsp;&nbsp;&nbsp;&nbsp;`{'universities': ['Berkeley, Stanford, Yale, University of Florida, ...'] }`
+&nbsp;&nbsp;&nbsp;&nbsp;`{'question': ['What were earnings per share in the most recent quarter?'] }  
 
-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.
+This model is finetuned on top of phi-3-mini-4k-instruct base.  
 
-For fast inference use, we would recommend the 'quantized tool' version, e.g.,  [**'slim-extract-tool'**](https://huggingface.co/llmware/slim-extract-tool).  
+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).  
 
 
 ## Prompt format:
 
-`function = "extract"`  
-`params = "{custom key}"`  
+`function = "generate"`  
+`params = "{'question', 'boolean', or 'multiple choice'}"`  
 `prompt = "<human> " + {text} + "\n" + `  
 &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; &nbsp; &nbsp; &nbsp;`"<{function}> " + {params} + "</{function}>" + "\n<bot>:"`  
 
@@ -27,11 +27,11 @@ For fast inference use, we would recommend the 'quantized tool' version, e.g.,
 <details>
 <summary>Transformers Script </summary>
 
-    model = AutoModelForCausalLM.from_pretrained("llmware/slim-extract")
-    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-extract")
+    model = AutoModelForCausalLM.from_pretrained("llmware/slim-q-gen-phi-3")
+    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-q-gen-phi-3")
 
-    function = "extract"
-    params = "company"
+    function = "generate"
+    params = "boolean"
 
     text = "Tesla stock declined yesterday 8% in premarket trading after a poorly-received event in San Francisco yesterday, in which the company indicated a likely shortfall in revenue."  
     
@@ -53,6 +53,8 @@ For fast inference use, we would recommend the 'quantized tool' version, e.g.,
 
     print("output only: ", output_only)  
 
+    `{'llm_response': {'question': ['Did Telsa stock decline more than 8% yesterday?']} }`  
+    
     # here's the fun part
     try:
         output_only = ast.literal_eval(llm_string_output)
@@ -70,8 +72,8 @@ 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-extract")
-    response = slim_model.function_call(text,params=["company"], function="extract")
+    slim_model = ModelCatalog().load_model("llmware/slim-q-gen-phi-3")
+    response = slim_model.function_call(text,params=["boolean"], function="generate")
 
     print("llmware - llm_response: ", response)