Upload README.md

README.md

@@ -1,118 +1,87 @@
 ---
-license: apache-2.0  
-inference: false  
+license: apache-2.0
+inference: false
 ---
 
-# dragon-phi-3-answer-tool
+# SLIM-Q-GEN-PHI-3  
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-dragon-phi-3-answer-tool is part of the DRAGON ("Delivering RAG On ...") model series, RAG-instruct trained on top of a Microsoft Phi-3 base model.
+**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.,  
 
-DRAGON models are fine-tuned with high-quality custom instruct datasets, designed for production use in RAG scenarios.
+&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.  
 
-### Benchmark Tests  
+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).  
 
-Evaluated against the benchmark test:   [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/rag_instruct_benchmark_tester)  
-Average of 2 Test Runs with 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations.  
 
---**Accuracy Score**:  **100.0** correct out of 100  
---Not Found Classification:  95.0%  
---Boolean:  97.5%  
---Math/Logic:  80.0%  
---Complex Questions (1-5):  4 (Above Average - multiple-choice, causal)  
---Summarization Quality (1-5):  4 (Above Average)  
---Hallucinations:  No hallucinations observed in test runs.  
+## Prompt format:
 
-For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).
+`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>:"`  
 
-### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+<details>
+<summary>Transformers Script </summary>
 
-- **Developed by:** llmware
-- **Model type:** Dragon 
-- **Language(s) (NLP):** English
-- **License:** Apache 2.0
-- **Finetuned from model:** Microsoft Phi-3
+    model = AutoModelForCausalLM.from_pretrained("llmware/slim-q-gen-phi-3")
+    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-q-gen-phi-3")
 
-## Uses
+    function = "generate"
+    params = "boolean"
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+    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."  
+    
+    prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"
 
-The intended use of BLING models is two-fold:
+    inputs = tokenizer(prompt, return_tensors="pt")
+    start_of_input = len(inputs.input_ids[0])
 
-1.  Provide high-quality RAG-Instruct models designed for fact-based, no "hallucination" question-answering in connection with an enterprise RAG workflow.
-
-2.  BLING models are fine-tuned on top of leading base foundation models, generally in the 1-3B+ range, and purposefully rolled-out across multiple base models to provide choices and "drop-in" replacements for RAG specific use cases.
-
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-BLING is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services,
-legal and regulatory industries with complex information sources.  
-
-BLING models have been trained for common RAG scenarios, specifically:   question-answering, key-value extraction, and basic summarization as the core instruction types
-without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
-
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms.
-
-
-## How to Get Started with the Model
-
-The fastest way to get started with BLING is through direct import in transformers:
-
-    from transformers import AutoTokenizer, AutoModelForCausalLM  
-    tokenizer = AutoTokenizer.from_pretrained("bling-phi-2-v0", trust_remote_code=True)  
-    model = AutoModelForCausalLM.from_pretrained("bling-phi-2-v0", trust_remote_code=True)  
-
-Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model.  The **generation_test_llmware_script.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.  
-
-The dRAGon model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
-
-    full_prompt = "<human>: " + my_prompt + "\n" + "<bot>:"
-
-The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts:
-
-1.  Text Passage Context, and
-2.  Specific question or instruction based on the text passage
+    outputs = model.generate(
+        inputs.input_ids.to('cpu'),
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.eos_token_id,
+        do_sample=True,
+        temperature=0.7,
+        max_new_tokens=200
+    )
 
-To get the best results, package "my_prompt" as follows:
+    output_only = tokenizer.decode(outputs[0][start_of_input:], skip_special_tokens=True)
 
-    my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
+    print("output only: ", output_only)  
 
+    [OUTPUT]:  {'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)
+        print("success - converted to python dictionary automatically")
+    except:
+        print("fail - could not convert to python dictionary automatically - ", llm_string_output)
+   
+   </details>  
+ 
+<details>  
 
-If you are using a HuggingFace generation script:
 
-    # prepare prompt packaging used in fine-tuning process
-    new_prompt = "<human>: " + entries["context"] + "\n" + entries["query"] + "\n" + "<bot>:"
 
-    inputs = tokenizer(new_prompt, return_tensors="pt")  
-    start_of_output = len(inputs.input_ids[0])
+    
+<summary>Using as Function Call in LLMWare</summary>
 
-    #   temperature: set at 0.3 for consistency of output
-    #   max_new_tokens:  set at 100 - may prematurely stop a few of the summaries
+    from llmware.models import ModelCatalog
+    slim_model = ModelCatalog().load_model("llmware/slim-q-gen-phi-3", sample=True, temperature=0.7)  
+    response = slim_model.function_call(text,params=["boolean"], function="generate")  
 
-    outputs = model.generate(
-            inputs.input_ids.to(device),
-            eos_token_id=tokenizer.eos_token_id,
-            pad_token_id=tokenizer.eos_token_id,
-            do_sample=True,
-            temperature=0.3,
-            max_new_tokens=100,
-            )
-
-    output_only = tokenizer.decode(outputs[0][start_of_output:],skip_special_tokens=True)  
+    print("llmware - llm_response: ", response)  
 
+</details>  
 
+    
 ## Model Card Contact
 
-Darren Oberst & llmware team
+Darren Oberst & llmware team  
+
+[Join us on Discord](https://discord.gg/MhZn5Nc39h)