Titovs jdev8 commited on
Commit
016356f
1 Parent(s): bff9db4

Update README.md (#4)

Browse files

- Update README.md (76d7a33ae9dedee6a894cd4c6b9731824f151bb4)


Co-authored-by: Anton Shapkin <jdev8@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +25 -18
README.md CHANGED
@@ -10,24 +10,31 @@ This is a repository for fine-tuned CodeLlama-7b model in the Hugging Face Trans
10
  # Model use
11
 
12
  ```python
13
- from transformers import AutoModelForCausalLM, AutoTokenizer
14
-
15
- # Load pre-trained model and tokenizer
16
- model_name = 'JetBrains/CodeLlama-7B-Kexer' # Replace with the desired model name
17
- tokenizer = AutoTokenizer.from_pretrained(model_name)
18
- model = AutoModelForCausalLM.from_pretrained(model_name).cuda()
19
-
20
- # Encode input text
21
- input_text = """This function takes an integer n and returns factorial of a number:
22
- fun factorial(n: Int): Int {"""
23
- input_ids = tokenizer.encode(input_text, return_tensors='pt').to('cuda')
24
-
25
- # Generate text
26
- output = model.generate(input_ids, max_length=150, num_return_sequences=1, no_repeat_ngram_size=2, early_stopping=True)
27
-
28
- # Decode and print the generated text
29
- generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
30
- print(generated_text)
 
 
 
 
 
 
 
31
  ```
32
 
33
  # Training setup
 
10
  # Model use
11
 
12
  ```python
13
+ from transformers import AutoModelForCausalLM, AutoTokenizer
14
+
15
+ # Load pre-trained model and tokenizer
16
+ model_name = 'JetBrains/CodeLlama-7B-Kexer'
17
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
18
+ model = AutoModelForCausalLM.from_pretrained(model_name).to('cuda')
19
+
20
+ # Create and encode input
21
+ input_text = """\
22
+ This function takes an integer n and returns factorial of a number:
23
+ fun factorial(n: Int): Int {\
24
+ """
25
+ input_ids = tokenizer.encode(
26
+ input_text, return_tensors='pt'
27
+ ).to('cuda')
28
+
29
+ # Generate
30
+ output = model.generate(
31
+ input_ids, max_length=150, num_return_sequences=1,
32
+ no_repeat_ngram_size=2, early_stopping=True
33
+ )
34
+
35
+ # Decode output
36
+ generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
37
+ print(generated_text)
38
  ```
39
 
40
  # Training setup