Update README.md
Browse files
README.md
CHANGED
@@ -51,16 +51,16 @@ messages = [
|
|
51 |
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
52 |
outputs = pipe(prompt, max_new_tokens=256, do_sample=False)
|
53 |
print(outputs[0]["generated_text"])
|
54 |
-
|
55 |
-
#A virtual assistant answers questions from a user based on the provided text.</s>
|
56 |
-
|
57 |
-
#Text: The American Bank Note Company Printing Plant is a repurposed complex of three interconnected buildings in the Hunts Point neighborhood of the Bronx in New York City. The innovative Kirby, Petit & Green design was built in 1909–1911 by the American Bank Note Company on land which had previously been part of Edward G. Faile's country estate. A wide variety of financial instruments were printed there; at one point, over five million documents were produced per day, including half the securities traded on the New York Stock Exchange.</s>
|
58 |
-
|
59 |
-
#I've read this text.</s>
|
60 |
-
|
61 |
-
#What describes location in the text?</s>
|
62 |
-
|
63 |
-
#["Hunts Point", "Bronx", "New York City"]
|
64 |
```
|
65 |
|
66 |
### Note: Inferences are based on one entity type at a time. For multiple entity types, create separate instances for each type.
|
|
|
51 |
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
52 |
outputs = pipe(prompt, max_new_tokens=256, do_sample=False)
|
53 |
print(outputs[0]["generated_text"])
|
54 |
+
# <|system|>
|
55 |
+
# A virtual assistant answers questions from a user based on the provided text.</s>
|
56 |
+
# <|user|>
|
57 |
+
# Text: The American Bank Note Company Printing Plant is a repurposed complex of three interconnected buildings in the Hunts Point neighborhood of the Bronx in New York City. The innovative Kirby, Petit & Green design was built in 1909–1911 by the American Bank Note Company on land which had previously been part of Edward G. Faile's country estate. A wide variety of financial instruments were printed there; at one point, over five million documents were produced per day, including half the securities traded on the New York Stock Exchange.</s>
|
58 |
+
# <|assistant|>
|
59 |
+
# I've read this text.</s>
|
60 |
+
# <|user|>
|
61 |
+
# What describes location in the text?</s>
|
62 |
+
# <|assistant|>
|
63 |
+
# ["Hunts Point", "Bronx", "New York City"]
|
64 |
```
|
65 |
|
66 |
### Note: Inferences are based on one entity type at a time. For multiple entity types, create separate instances for each type.
|