updated readme

README.md

@@ -6,7 +6,7 @@ language: en
 # BART-SLED (SLiding-Encoder and Decoder, base-sized model) 
 
 SLED models use pretrained, short-range encoder-decoder models, and apply them over 
-long-text inputs by splitting the input into multiple overlapping chunks, encoding each independtly and perform fusion-in-decoder
+long-text inputs by splitting the input into multiple overlapping chunks, encoding each independently and perform fusion-in-decoder
 
 ## Model description
 
@@ -19,7 +19,19 @@ well for comprehension tasks (e.g. text classification, question answering). Whe
 You can use the raw model for text infilling. However, the model is mostly meant to be fine-tuned on a supervised dataset. 
 
 ### How to use
-To use the model, you first have to get a local copy of the SLED model from the [official repository](https://github.com/Mivg/SLED/blob/main/README.md).
+To use the model, you first need to install `sled-py` in your environment (or clone the code from the [official repository](https://github.com/Mivg/SLED/blob/main/README.md))
+```
+pip install sled-py
+```
+For more installation instructions, see [here](https://github.com/Mivg/SLED#Installation).
+
+
+Once installed, SLED is fully compatible with HuggingFace's AutoClasses (AutoTokenizer, AutoConfig, AutoModel 
+and AutoModelForCausalLM) and can be loaded using the from_pretrained methods
+```python
+import sled   # *** required so that SledModels will be registered for the AutoClasses ***
+model = AutoModel.from_pretrained('tau/bart-base-sled')
+```
 
 Here is how to use this model in PyTorch:
 
@@ -32,12 +44,25 @@ outputs = model(**inputs)
 last_hidden_states = outputs.last_hidden_state
 ```
 You can also replace SledModel by SledModelForConditionalGeneration for Seq2Seq generation 
-
+```python
+model = SledModelForConditionalGeneration.from_pretrained('tau/bart-base-sled')
+```
 In case you wish to apply SLED on a task containing a prefix (e.g. question) which should be given as a context to 
 every chunk, you can pass the `prefix_length` tensor input as well (A LongTensor in the length of the batch size).
+```python
+import torch
+import sled   # *** required so that SledModels will be registered for the AutoClasses ***
+tokenizer = AutoTokenizer.from_pretrained('tau/bart-base-sled')
+model = AutoModel.from_pretrained('tau/bart-base-sled')
+document_input_ids = tokenizer("Dogs are great for you.", return_tensors="pt").input_ids
+prefix_input_ids = tokenizer("Are dogs good for you?", return_tensors="pt").input_ids
+input_ids = torch.cat((prefix_input_ids, document_input_ids), dim=-1)
+attention_mask = torch.ones_like(input_ids)
+prefix_length = torch.LongTensor([[prefix_input_ids.size(1)]])
 
-Sled is fully compatible with the AutoClasses (AutoTokenizer, AutoConfig, AutoModel 
-and AutoModelForCausalLM) and can be loaded using the from_pretrained methods
+outputs = model(input_ids=input_ids, attention_mask=attention_mask, prefix_length=prefix_length)
+last_hidden_states = outputs.last_hidden_state
+```
 
 ### BibTeX entry and citation info