Update Readme.md

README.md

@@ -3,10 +3,11 @@ license: apache-2.0
 language:
 - en
 metrics:
-- rouge
+- Rouge
 pipeline_tag: summarization
 tags:
 - t5
+- t5-small
 - summarization
 - medical-research
 ---
@@ -25,20 +26,18 @@ This modelcard aims to be a base template for new models. It has been generated
 This is a text generative model to summarize long abstract from medical jourals into one liners. These one liners can be used as titles in the journal.
 
 
-- **Developed by:** [Tushar Joshi]
-- **Shared by [optional]:** [Tushar Joshi]
-- **Model type:** [T5]
-- **Language(s) (NLP):** [English]
-- **License:** [Apache 2.9]
-- **Finetuned from model [optional]:** [T5 Baseline]
+- **Developed by:** Tushar Joshi
+- **Shared by [optional]:** Tushar Joshi
+- **Model type:** t5-small
+- **Language(s) (NLP):** English
+- **License:** Apache 2.0
+- **Finetuned from model [optional]:** t5-small baseline
 
 ### Model Sources [optional]
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** https://huggingface.co/t5-small
 
 ## Uses
 
@@ -49,26 +48,21 @@ This is a text generative model to summarize long abstract from medical jourals
 ### Direct Use
 
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+* As a text summarizer for medical abstracts and journals.
 
-[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
 
 <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-[More Information Needed]
+Should not be used as a text summarizer for very long tasks. Maximum token size of 1024. 
 
 ## Bias, Risks, and Limitations
 
 <!-- This section is meant to convey both technical and sociotechnical limitations. -->
+* Max input token size of 1024
+* Max output token size of 24
 
-[More Information Needed]
 
 ### Recommendations
 
@@ -80,46 +74,56 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 Use the code below to get started with the model.
 
-[More Information Needed]
+```
+from transformers import pipeline
+text = """Text that needs to be summarized"""
+
+summarizer = pipeline("summarization", model="path-to-model")
+summary = summarizer(text)[0]["summary_text"]
+
+print (summary)
+```
 
 ## Training Details
 
 ### Training Data
 
 <!-- This should link to a Data 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]
+The training data is internally curated and canot be exposed.
 
 ### Training Procedure 
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+None
 
 #### Preprocessing [optional]
-
-[More Information Needed]
+None
 
 
 #### Training Hyperparameters
 
 - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+- None
 
 #### Speeds, Sizes, Times [optional]
 
 <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
 
-[More Information Needed]
+The training was done using GPU T4x 2. The task took 4:09:47 to complete. The dataset size of 10,000 examples was used for training the generative model.
 
 ## Evaluation
 
 <!-- This section describes the evaluation protocols and provides the results. -->
+The quality of summarization was tested on 5000 medical journals created over last 20 years. The data of medical jounals is scraped from various sources.
 
 ### Testing Data, Factors & Metrics
 
+Test Data Size: 5000 examples
+
 #### Testing Data
 
 <!-- This should link to a Data Card if possible. -->
-
-[More Information Needed]
+The testing data is internally generated and curated.
 
 #### Factors
 
@@ -130,6 +134,28 @@ Use the code below to get started with the model.
 #### Metrics
 
 <!-- These are the evaluation metrics being used, ideally with a description of why. -->
+The model was evaluated on Rouge Metrics below are the baseline results achieved
+Epoch	Training Loss	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
+1	4.160200	2.802442	0.255200	0.101900	0.233100	0.233200	15.500300
+2	2.962400	2.645199	0.288200	0.118300	0.262600	0.262600	15.827100
+3	2.820600	2.578758	0.295200	0.121800	0.268400	0.268500	16.218300
+4	2.776400	2.533263	0.302900	0.125800	0.275500	0.275400	16.341800
+5	2.699700	2.504000	0.304600	0.127300	0.277300	0.277100	16.410100
+6	2.664700	2.473418	0.306900	0.129800	0.280200	0.280100	16.354000
+7	2.619600	2.454723	0.307700	0.131000	0.280400	0.280400	16.526000
+8	2.591600	2.435169	0.310700	0.133200	0.283300	0.283400	16.441900
+9	2.571600	2.419672	0.309200	0.132000	0.281900	0.281700	16.402300
+10	2.548000	2.412395	0.309400	0.132900	0.282200	0.282300	16.325600
+11	2.535200	2.402286	0.309600	0.132300	0.282100	0.282000	16.377400
+12	2.508700	2.396766	0.310700	0.132600	0.283100	0.283200	16.459200
+13	2.486500	2.389850	0.311700	0.133900	0.284100	0.284200	16.458600
+14	2.508100	2.388508	0.312400	0.133700	0.284500	0.284500	16.407200
+15	2.474800	2.379151	0.313100	0.134000	0.285000	0.284900	16.457200
+16	2.469000	2.378473	0.311900	0.133300	0.284100	0.284000	16.390700
+17	2.458700	2.376562	0.311500	0.133400	0.283500	0.283400	16.448800
+18	2.442800	2.375408	0.313700	0.134600	0.285400	0.285400	16.414100
+19	2.454800	2.372553	0.312900	0.134100	0.284900	0.285000	16.445100
+20	2.438900	2.372551	0.312300	0.134000	0.284500	0.284600	16.435500
 
 [More Information Needed]
 
@@ -153,11 +179,11 @@ Use the code below to get started with the model.
 
 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).
 
-- **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]
+- **Hardware Type:** GPU T4 x 2
+- **Hours used:** 4.5
+- **Cloud Provider:** GCP
+- **Compute Region:** Ireland
+- **Carbon Emitted:** Unknown
 
 ## Technical Specifications [optional]
 
@@ -201,10 +227,11 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Authors [optional]
 
-[More Information Needed]
+Tushar Joshi
 
 ## Model Card Contact
 
-[More Information Needed]
+Tushar Joshi
+LinkedIn - https://www.linkedin.com/in/tushar-joshi-816133100/