umarigan commited on
Commit
441b454
1 Parent(s): 97762e9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +42 -1
README.md CHANGED
@@ -23,4 +23,45 @@ datasets:
23
 
24
  This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
25
 
26
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
 
24
  This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
25
 
26
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
27
+
28
+
29
+ ## Usage Examples
30
+
31
+ ```python
32
+
33
+ # Load model directly
34
+ from transformers import AutoTokenizer, AutoModelForCausalLM
35
+
36
+ tokenizer = AutoTokenizer.from_pretrained("umarigan/LLama-3-8B-Instruction-tr")
37
+ model = AutoModelForCausalLM.from_pretrained("umarigan/LLama-3-8B-Instruction-tr")
38
+ alpaca_prompt = """
39
+ Görev:
40
+ {}
41
+
42
+ Girdi:
43
+ {}
44
+
45
+ Cevap:
46
+ {}"""
47
+
48
+ inputs = tokenizer(
49
+ [
50
+ alpaca_prompt.format(
51
+ "bir haftada 3 kilo verebileceğim 5 öneri sunabilir misin?", # Görev
52
+ "", # Girdi
53
+ "", # Cevap - boş bırakın!
54
+ )
55
+ ], return_tensors = "pt")
56
+ outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
57
+ tokenizer.batch_decode(outputs)
58
+
59
+ Output:
60
+ <|begin_of_text|> Görev: bir haftada 3 kilo verebileceğim 5 öneri sunabilir misin?
61
+
62
+ Girdi:
63
+
64
+ Cevap:
65
+
66
+ 1. Yemeklerinizde daha az tuz kullanın. 2. Daha fazla sebze ve meyve tüketin. 3. Daha fazla su için. 4. Daha fazla egzersiz yapın. 5. Daha fazla uyku alın.<|end_of_text|>
67
+ ```