Update README.md

README.md

@@ -21,17 +21,33 @@ It achieves the following results on the evaluation set:
 - Loss: 0.7894
 - Num Input Tokens Seen: 14258488
 
-## Model description
+```py
+from transformers import pipeline
 
-More information needed
+model_name = "pszemraj/bart-large-summary-map-reduce-1024"
+# model_name = "pszemraj/flan-t5-large-summary-map-reduce-1024"
 
-## Intended uses & limitations
+pipe = pipeline("text2text-generation", model=model_name, device_map="auto")
 
-More information needed
+text = """This dissertation examines the relationship between post-war American and British film noir films, focusing on Alfred Zinnemann (Act of Violence) and Carol Reed (The Man Between). It explores the intersection between these films' depictions of material reality and their protagonists' shifts through urban spaces. The thesis argues that both films represent an awareness of tensions in their materiality, which can lead to disengagement and a renegotiation of identities. However, both films fail to emphasize mental disintegration as a common source or goal.
 
-## Training and evaluation data
+The film "The Man Between," directed by Carol Reed, explores the relationship between material reality and character development in a post-war urban setting. The protagonist, Ivo, distances himself from physical reality through speed of motion, while Susanne, a German citizen, moves between suburbia and city. Both films explore themes of alienation and reparativeity, emphasizing the importance of engaging with material reality rather than distancing oneself from it.
+"""
 
-More information needed
+text = """A computer implemented method of generating a syntactic object. The method includes the steps of providing a plurality of input data sets, each input data set comprising one or more words, wherein each word is associated with at least one non-adjacent second word; creating an exocentric relationship between the first and second words by applying a neo-ian event semantics to the input data in such a way that the neo-antagonistic effect results in the generation of the syntactic object; and storing the generated syntactic object for future use.
+	A method of learning and using language is disclosed. The method includes the steps of creating a lexicon of words, wherein each word in the lexicon has at least two possible states, selecting a set of one or more of the possible states of the lexicon to be used as a base state for a subsequent computational operation, and applying the computational operation to the base state to form a new output state.
+	A computer implemented method for changing a first workspace to a second workspace. The method includes the steps of creating a new workspace by merging the first workspace with the second workspace, wherein the merging is based on at least one of: an impenetrable condition; a constraint on movement; and a resource restriction.
+	The brain is constantly loosing neurons because you doesn't want all the junk around."""
+
+import torch
+import textwrap
+
+torch.cuda.is_available()
+res = pipe(text, max_new_tokens=500, num_beams=4, early_stopping=True)
+textwrap.wrap(res[0]["generated_text"], width=100)
+
+res[0]["generated_text"]
+```
 
 ## Training procedure