jdev8 commited on
Commit
422a12d
1 Parent(s): a6f080d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -10
README.md CHANGED
@@ -2,9 +2,33 @@
2
  license: apache-2.0
3
  ---
4
 
5
- # Model summary
6
 
7
- This is CodeLlama model fine-tuned on Kotlin Exercices dataset.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
 
9
  # Training setup
10
 
@@ -20,7 +44,7 @@ The model was trained on one A100 GPU with following hyperparameters:
20
 
21
  # Fine-tuning data
22
 
23
- For this model we used 15K exmaples of Kotlin Exercices dataset. For more information about the dataset follow th link.
24
 
25
  # Evaluation
26
 
@@ -28,10 +52,7 @@ To evaluate we used Kotlin Humaneval (more infromation here)
28
 
29
  Fine-tuned model:
30
 
31
- **Kotlin Humaneval: 42.24**
32
- **Kotlin Compleation: 0.344**
33
-
34
- Base model:
35
-
36
- **Kotlin Humaneval: 26.89**
37
- **Kotlin Compleation: 0.388**
 
2
  license: apache-2.0
3
  ---
4
 
5
+ # Kexer models
6
 
7
+ Kexer models is a collection of fine-tuned open-source generative text models fine-tuned on Kotlin Exercices dataset.
8
+ This is a repository for fine-tuned CodeLlama-7b model in the Hugging Face Transformers format.
9
+
10
+ # Model use
11
+
12
+ ```
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
34
 
 
44
 
45
  # Fine-tuning data
46
 
47
+ For this model we used 15K exmaples of Kotlin Exercices dataset {TODO: link!}. For more information about the dataset follow th link.
48
 
49
  # Evaluation
50
 
 
52
 
53
  Fine-tuned model:
54
 
55
+ | **Model name** | **Kotlin HumanEval Pass Rate** | **Kotlin Completion** |
56
+ |:---------------------------:|:----------------------------------------:|:----------------------------------------:|
57
+ | `base model` | 26.89 | 0.388 |
58
+ | `fine-tuned model` | 42.24 | 0.344 |