Sharathhebbar24 commited on
Commit
ffaaa33
1 Parent(s): ac83f3d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -9
README.md CHANGED
@@ -11,9 +11,10 @@ pipeline_tag: text-generation
11
  tags:
12
  - gpt2
13
  - dpo
 
14
  ---
15
 
16
- This model is a finetuned version of ```Sharathhebbar24/chat_gpt2_dpo``` using ```mlabonne/CodeLlama-2-20k```
17
 
18
  ## Model description
19
 
@@ -34,7 +35,7 @@ prompt.
34
 
35
  ```python
36
  >>> from transformers import AutoTokenizer, AutoModelForCausalLM
37
- >>> model_name = "Sharathhebbar24/chat_gpt2"
38
  >>> model = AutoModelForCausalLM.from_pretrained(model_name)
39
  >>> tokenizer = AutoTokenizer.from_pretrained(model_name)
40
  >>> def generate_text(prompt):
@@ -42,13 +43,7 @@ prompt.
42
  >>> outputs = model.generate(inputs, max_length=64, pad_token_id=tokenizer.eos_token_id)
43
  >>> generated = tokenizer.decode(outputs[0], skip_special_tokens=True)
44
  >>> return generated[:generated.rfind(".")+1]
45
- >>> prompt = """
46
- >>> user: what are you?
47
- >>> assistant: I am a Chatbot intended to give a python program
48
- >>> user: hmm, can you write a python program to print Hii Heloo
49
- >>> assistant: Sure Here is a python code.\n print("Hii Heloo")
50
- >>> user: Can you write a Linear search program in python
51
- >>> """
52
  >>> res = generate_text(prompt)
53
  >>> res
54
  ```
 
11
  tags:
12
  - gpt2
13
  - dpo
14
+ - code
15
  ---
16
 
17
+ This model is a finetuned version of [Sharathhebbar24/code_gpt2_mini_model](https://huggingface.co/Sharathhebbar24/code_gpt2_mini_model) using [Sharathhebbar24/Evol-Instruct-Code-80k-v1](https://huggingface.co/datasets/Sharathhebbar24/Evol-Instruct-Code-80k-v1)
18
 
19
  ## Model description
20
 
 
35
 
36
  ```python
37
  >>> from transformers import AutoTokenizer, AutoModelForCausalLM
38
+ >>> model_name = "Sharathhebbar24/code_gpt2"
39
  >>> model = AutoModelForCausalLM.from_pretrained(model_name)
40
  >>> tokenizer = AutoTokenizer.from_pretrained(model_name)
41
  >>> def generate_text(prompt):
 
43
  >>> outputs = model.generate(inputs, max_length=64, pad_token_id=tokenizer.eos_token_id)
44
  >>> generated = tokenizer.decode(outputs[0], skip_special_tokens=True)
45
  >>> return generated[:generated.rfind(".")+1]
46
+ >>> prompt = "Can you write a Linear search program in Python"
 
 
 
 
 
 
47
  >>> res = generate_text(prompt)
48
  >>> res
49
  ```