NotASI commited on
Commit
c74bfdf
1 Parent(s): a8e0c2d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -1
README.md CHANGED
@@ -33,4 +33,89 @@ This model follows the same chat template as the base model one.
33
 
34
  This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
35
 
36
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
 
34
  This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
35
 
36
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
37
+
38
+ # Usage
39
+
40
+ **Dependencies**
41
+
42
+ ```
43
+ !pip install unsloth
44
+ !pip install --upgrade "transformers>=4.45"
45
+ ```
46
+
47
+ **Code**
48
+
49
+ ```python
50
+ from unsloth.chat_templates import get_chat_template
51
+ from unsloth import FastLanguageModel
52
+ import torch
53
+
54
+ model, tokenizer = FastLanguageModel.from_pretrained(
55
+ model_name = "NotASI/FineTome-Llama3.2-1B-0929",
56
+ )
57
+
58
+ tokenizer = get_chat_template(
59
+ tokenizer,
60
+ chat_template = "llama-3.1",
61
+ )
62
+ FastLanguageModel.for_inference(model) # Enable native 2x faster inference
63
+
64
+ messages = [
65
+ {"role": "user", "content": "<message>"},
66
+ ]
67
+ inputs = tokenizer.apply_chat_template(
68
+ messages,
69
+ tokenize = True,
70
+ add_generation_prompt = True, # Must add for generation
71
+ return_tensors = "pt",
72
+ ).to("cuda")
73
+
74
+ from transformers import TextStreamer
75
+ text_streamer = TextStreamer(tokenizer, skip_prompt = True)
76
+ _ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 128,
77
+ use_cache = True, temperature = 1.5, min_p = 0.1)
78
+ ```
79
+
80
+ ## Examples 1
81
+
82
+ **Input**:
83
+ ```
84
+ Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8. Give me the next 10 numbers.
85
+ ```
86
+
87
+ **Output**:
88
+ ```
89
+ Here are the next 10 numbers in the Fibonacci sequence:
90
+
91
+ 1. 13
92
+ 2. 21
93
+ 3. 34
94
+ 4. 55
95
+ 5. 89
96
+ 6. 144
97
+ 7. 233
98
+ 8. 377
99
+ 9. 610
100
+ 10. 987
101
+ 11. 1597
102
+ 12. 2584
103
+ 13. 4190
104
+ 14. 6765
105
+ 15. 10946
106
+ 16. 17715
107
+
108
+ Explanation: The Fibonacci sequence is a series of numbers where each number is the sum of the two preceding ones, starting from 0 and 1. To calculate the nth Fibonacci number, you can use the formula F(n) = F(n-1) + F(n-2).<|eot_id|>
109
+ ```
110
+
111
+ ## Example 2
112
+
113
+ **Input**:
114
+ ```
115
+ Who are you? Briefy introduce yourself.
116
+ ```
117
+
118
+ **Output**:
119
+ ```
120
+ Hi there! I'm an AI assistant designed to help with a range of inquiries. As for your request to introduce yourself briefly, I can certainly do that. I am a highly advanced AI, capable of understanding and processing vast amounts of information. My purpose is to provide useful and informative responses to the users' questions.<|eot_id|>
121
+ ```