Update README.md

README.md

@@ -39,6 +39,10 @@ widget:
       It's not certain how many lessons you'll learn by your thirties. Does the
       premise entail the hypothesis?
     example_title: Premise and hypothesis
+  - text: >-
+      Answer the following question by reasoning step by step. 
+      The cafeteria had 23 apples. If they used 20 for lunch, and bought 6 more, how many apple do they have?
+    example_title: Chain of thought
 tags:
   - text2text-generation
 datasets:
@@ -56,17 +60,21 @@ datasets:
 license: apache-2.0
 ---
 
-# TL;DR FLan-UL2 improvements over previous version
-The original UL2 model was only trained with receptive field of 512, which made it non-ideal for N-shot prompting where N is large. 
-This Flan-UL2 checkpoint uses a receptive field of 2048 which makes it more usable for few-shot in-context learning.
-
-The original UL2 model also had mode switch tokens that was rather mandatory to get good performance.
-However, they were a little cumbersome as this requires often some changes during inference or finetuning. In this update/change, we continue training UL2 20B for an additional 100k steps (with small batch) to forget “mode tokens” before applying Flan instruction tuning. This Flan-UL2 checkpoint does not require mode tokens anymore.
+# TL;DR FLan-UL2
+Flan-UL2 is an encoder decoder model based on the `T5` architecture. It uses the same configuration as the [`UL2 model`](https://huggingface.co/google/ul2)  released earlier last year. It was fine tuned using the "Flan" prompt tuning 
+and dataset collection.
 
-# Converting from T5x to huggingface
-You can use the [`convert_`]() and pass the argument `strict = False`. The final layer norm is missing from the original dictionnary, we used an identity layer. 
+According ot the original [blog]() here are the notable improvements:
+- The original UL2 model was only trained with receptive field of 512, which made it non-ideal for N-shot prompting where N is large. 
+- The Flan-UL2 checkpoint uses a receptive field of 2048 which makes it more usable for few-shot in-context learning.
+- The original UL2 model also had mode switch tokens that was rather mandatory to get good performance. However, they were a little cumbersome as this requires often some changes during inference or finetuning. In this update/change, we continue training UL2 20B for an additional 100k steps (with small batch) to forget “mode tokens” before applying Flan instruction tuning. This Flan-UL2 checkpoint does not require mode tokens anymore.
 
-# Performance improvment 
+## Converting from T5x to huggingface
+You can use the [`convert_t5x_checkpoint_to_pytorch.py`](https://github.com/huggingface/transformers/blob/main/src/transformers/models/t5/convert_t5x_checkpoint_to_pytorch.py) script and pass the argument `strict = False`. The final layer norm is missing from the original dictionnary, that is why we are passing the `stric=False` argument.
+```bash
+python convert_t5x_checkpoint_to_pytorch.py --t5x_checkpoint_path ~/code/ul2/flan-ul220b-v3/ --config_file config.json --pytorch_dump_path ~/code/ul2/flan-ul2
+```
+## Performance improvment 
 
 The reported results are the following : 
 |  | MMLU | BBH | MMLU-CoT | BBH-CoT | Avg |
@@ -76,8 +84,26 @@ The reported results are the following :
 | FLAN-T5-XXL 11B | 55.1 | 45.3 | 48.6 | 41.4 | 47.6 |
 | FLAN-UL2 20B | 55.7(+1.1%) | 45.9(+1.3%) | 52.2(+7.4%) | 42.7(+3.1%) | 49.1(+3.2%) |
 
+# Using the model 
+
+```python
+from transformers import AutoModelForConditionalGeneration, AutoTokenizer
+import torch
+model = AutoModelForConditionalGeneration.from_pretrained("google/flan-ul2", device_map="auto", load_in_8bits = True)                                                                 
+tokenizer = AutoTokenizer.from_pretrained("google/flan-ul2")
+
+input_string = "Answer the following question by reasoning step by step. The cafeteria had 23 apples. If they used 20 for lunch, and bought 6 more, how many apple do they have?"                                               
+
+inputs = tokenizer(input_string, return_tensors="pt").input_ids.to("cuda")
+outputs = model.generate(inputs, max_length=200)
+
+print(tokenizer.decode(outputs[0]))
+# <pad> They have 23 - 20 = 3 apples left. They have 3 + 6 = 9 apples. Therefore, the answer is 9.</s>
+
+```
 
-# Introduction
+
+# Introduction to UL2
 
 UL2 is a unified framework for pretraining models that are universally effective across datasets and setups. UL2 uses Mixture-of-Denoisers (MoD), apre-training objective that combines diverse pre-training paradigms together. UL2 introduces a notion of mode switching, wherein downstream fine-tuning is associated with specific pre-training schemes.
 
@@ -95,9 +121,12 @@ Authors: *Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Dara Bahri, Tal
 
 # Training
 
-## Flan UL2, a 20B Flan trained UL2 model
+## Flan UL2
 The Flan-UL2 model was initialized using the `UL2` checkpoints, and was then trained additionally using Flan Prompting. This means that the original training corpus is `C4`, 
 
+In “Scaling Instruction-Finetuned language models (Chung et al.)�� (also referred to sometimes as the Flan2 paper), the key idea is to train a large language model on a collection of datasets. These datasets are phrased as instructions which enable generalization across diverse tasks. Flan has been primarily trained on academic tasks. In Flan2, we released a series of T5 models ranging from 200M to 11B parameters that have been instruction tuned with Flan.
+
+The Flan datasets have also been open sourced in “The Flan Collection: Designing Data and Methods for Effective Instruction Tuning” (Longpre et al.). See Google AI Blogpost: “The Flan Collection: Advancing Open Source Methods for Instruction Tuning”. 
 
 ## UL2 PreTraining
 
@@ -113,7 +142,7 @@ UL-20B was trained using the [Jax](https://github.com/google/jax) and [T5X](http
 
 The training objective during pretraining is a mixture of different denoising strategies that are explained in the following:
 
-## Mixture of Denoisers
+### Mixture of Denoisers
 
 To quote the paper:
 > We conjecture that a strong universal model has to be exposed to solving diverse set of problems
@@ -164,7 +193,7 @@ In total, the model was trained for 2.65 million steps.
 
 ## Contribution
 
-This model was contributed by [Younes Belkada](https://huggingface.co/Seledorn) & [Arthur Zucker]().
+This model was contributed by [Younes Belkada](https://huggingface.co/ybelkada) & [Arthur Zucker](https://huggingface.co/ArthurZ).
 
 ## Examples