Text Generation
Transformers
PyTorch
English
llama
text-generation-inference
minhtt32 commited on
Commit
254332b
·
verified ·
1 Parent(s): 6308448

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -1
README.md CHANGED
@@ -1,3 +1,65 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: cc-by-nc-4.0
3
+ language:
4
+ - en
5
+ datasets:
6
+ - Universal-NER/Pile-NER-type
7
  ---
8
+
9
+ ---
10
+
11
+
12
+ # UniNER-7B-all
13
+
14
+ **Description**: This model is self fine-tuned from [TinyLLama](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T). It is trained on ChatGPT-generated [Pile-NER-type data](https://huggingface.co/datasets/Universal-NER/Pile-NER-type).
15
+
16
+ Check our [paper](https://arxiv.org/abs/2308.03279) for more information.
17
+
18
+ ## Inference
19
+ # Install transformers from source - only needed for versions <= v4.34
20
+ # pip install git+https://github.com/huggingface/transformers.git
21
+ # pip install accelerate
22
+
23
+ import torch
24
+ from transformers import pipeline
25
+
26
+ pipe = pipeline("text-generation", model="/media/4TB_1/minhtt/Documents/test/axolotl/lora-out/merged",
27
+ torch_dtype=torch.bfloat16, device_map="auto")
28
+ # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
29
+ messages = [
30
+ {
31
+ "role": "system",
32
+ "content": "A virtual assistant answers questions from a user based on the provided text.",
33
+ },
34
+ {
35
+ "role": "user",
36
+ "content": "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."
37
+ },
38
+ {
39
+ "role": "assistant",
40
+ "content": "I've read this text."
41
+ },
42
+ {
43
+ "role": "user",
44
+ "content": "What describes location in the text?"
45
+ }
46
+ ]
47
+ prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
48
+ outputs = pipe(prompt, max_new_tokens=256, do_sample=False)
49
+ print(outputs[0]["generated_text"])
50
+ #<|system|>
51
+ #A virtual assistant answers questions from a user based on the provided text.</s>
52
+ #<|user|>
53
+ #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>
54
+ #<|assistant|>
55
+ #I've read this text.</s>
56
+ #<|user|>
57
+ #What describes location in the text?</s>
58
+ #<|assistant|>
59
+ #["Hunts Point", "Bronx", "New York City"]
60
+
61
+ ### Note: Inferences are based on one entity type at a time. For multiple entity types, create separate instances for each type.
62
+
63
+ ## License
64
+
65
+ This model and its associated data are released under the [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) license. They are primarily used for research purposes.