Update README.md

README.md

@@ -1,199 +1,174 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- text-generation
+- pytorch
+- small-evaluator
+- Patronus AI
+- evaluation
+- hallucination-detection
+license: cc-by-nc-4.0
+language:
+- en
+base_model:
+- microsoft/Phi-3.5-mini-instruct
+pipeline_tag: text-generation
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
+# Patronus GLIDER
 
+GLIDER is a fine tuned phi-3.5-mini-instruct which can be used as a general purpose evaluation model to judge texts, conversations and RAG setups according to arbitrary, user defined criteria and rubric scale. 
+This model was trained using a combination of synthetic and domain adapted data from popular datasets like Mocha, FinQA, Realtoxicity, etc.  The training data for this model covers over 183 metrics and 683+ domains including finance, medicine, and many more.
+The maximum sequence length is 8192 tokens but the model can support longer texts as well (tested upto 12,000 tokens). 
 
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Model Type:** GLIDER is a fine-tuned version of microsoft/Phi-3.5-mini-instruct model.
+- **Language:** Primarily English but supports Korean, Kazakh, Hindi, Bengali, Spanish, Indonesian, German, French, Arabic, Russian, Thai, Turkish, Ukraninan, Romainian and more.
+- **Developed by:** Patronus AI
+- **Paper:** [TBD]
+- **License:** [https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)
 
-### Model Sources [optional]
+### Model Sources
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
+- **Repository:** [https://github.com/patronus-ai/slm-evaluator](https://github.com/patronus-ai/slm-evaluator)
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
 ## How to Get Started with the Model
+To use the model, we recommend using the following prompt:
 
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
+```
+PROMPT = """Analyze the following pass criteria carefully and score the text based on the rubric defined below.
+
+To perform this evaluation, you must:
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+1. Understand the text tags, pass criteria and rubric thoroughly.
+2. Review the finer details of the text and the rubric.
+3. Compare the tags to be evaluated to the score descriptions in the rubric.
+4. Pay close attention to small details that might impact the final score and form accurate associations between tags and pass criteria.
+5. Write a detailed reasoning justifying your evaluation in a bullet point format. 
+6. The reasoning must summarize the overall strengths and weaknesses of the output while quoting exact phrases from the output wherever required.
+7. Output a list of words or phrases that you believe are the most important in determining the score.
+8. Assign a final score based on the scoring rubric.
 
-#### Preprocessing [optional]
+Data to evaluate:
+{data}
 
-[More Information Needed]
+Pass Criteria:
+{pass_criteria}
 
+Rubric:
+{rubric}
 
-#### Training Hyperparameters
+Your output must in the following format:
+<reasoning>
+[Detailed reasoning justifying your evaluation in a bullet point format according to the specifics defined above]
+</reasoning>
+<highlight>
+[List of words or phrases that you believe are the most important in determining the score]
+</highlight>
+<score>
+[The final integer score assigned based on the scoring rubric]
+</score>
+```
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+Since the model supports arbitrary number of inputs and outputs, the data can be structured in any one of the following ways:
 
-#### Speeds, Sizes, Times [optional]
+1. Conversational data:
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+```
+data = """<SYSTEM PROMPT>
+{system_prompt}
+</SYSTEM PROMPT>
 
-[More Information Needed]
+<USER PROMPT>
+{user_prompt}
+</USER PROMPT>
 
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
+<ASSISTANT REPLY>
+{assistant_response}
+</ASSISTANT REPLY>
+"""
+```
 
-[More Information Needed]
+This template can be adapted for arbitrary number of conversations by simply appending a numeric turn number as "<USER PROMPT 1>", "<USER PROMPT 2>" and so on. 
+Ensure that you specify the exact tags that you want the model to judge in the pass criteria
 
-#### Summary
+2. RAG system evaluation
 
+```
+data = """<CONTEXT>
+{retrieved_context}
+</CONTEXT>
 
+<USER INPUT>
+{user_input}
+</USER INPUT>
 
-## Model Examination [optional]
+<MODEL OUTPUT>
+{model_output}
+</MODEL OUTPUT>
+"""
+```
 
-<!-- Relevant interpretability work for the model goes here -->
+3. General purpose evaluations
 
-[More Information Needed]
+```
+data = """<USER INPUT>
+{input}
+</USER INPUT>
 
-## Environmental Impact
+<MODEL OUTPUT>
+{output}
+</MODEL OUTPUT>
+"""
+```
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+Note that these XML tags can be changed according to your convenience and task
 
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+## Inference
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+To run inference, you can use HF pipeline:
 
-## Technical Specifications [optional]
+```
 
-### Model Architecture and Objective
+model_name = 'PatronusAI/glider'
+pipe = pipeline(
+          "text-generation",
+          model=model_name,
+          max_new_tokens=2048,
+          device="cuda",
+          return_full_text=False
+        )
 
-[More Information Needed]
+messages = [
+    {"role": "user", "content": prompt},
+]
 
-### Compute Infrastructure
+result = pipe(messages)
+print(result[0]['generated_text'])
 
-[More Information Needed]
+```
 
-#### Hardware
+Since the model is trained in chat format, ensure that you pass the prompt as a user message.
 
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
+## Evaluation
 
-## More Information [optional]
+The model was evaluated on several popular datasets:
 
-[More Information Needed]
+<img src="https://i.imgur.com/wsv3COh.png" alt="Likert Rating Results" width="50%"/>
+<img src="https://i.imgur.com/xmxREho.png" alt="Pairwise Comparisons" width="50%"/>
 
-## Model Card Authors [optional]
+## Citation
+If you are using the model, cite using
 
-[More Information Needed]
+```
+[Paper citation]
+```
 
 ## Model Card Contact
-
-[More Information Needed]
+[@darshandeshpande](https://huggingface.co/darshandeshpande)
+[@RebeccaQian1](https://huggingface.co/RebeccaQian1)