YashikaNagpal commited on
Commit
46e674f
·
verified ·
1 Parent(s): 5512374

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -8
README.md CHANGED
@@ -35,6 +35,8 @@ T5ForConditionalGeneration(
35
  (lm_head): Linear(in_features=768, out_features=32100, bias=False)
36
  )
37
 
 
 
38
  ```bash
39
  pip install -U transformers torch datasets
40
  #Then, load the model and run inference:
@@ -43,7 +45,7 @@ from transformers import T5ForConditionalGeneration, RobertaTokenizer
43
 
44
  # Download from the 🤗 Hub
45
  ```python
46
- model_name = "your-username/codet5-conala-comments" # Update with your HF model ID
47
  tokenizer = RobertaTokenizer.from_pretrained(model_name)
48
  model = T5ForConditionalGeneration.from_pretrained(model_name)
49
 
@@ -91,11 +93,11 @@ snippet: int(''.join(map(str, x))), rewritten_intent: "Convert a list of integer
91
  snippet: datetime.strptime('2010-11-13 10:33:54.227806', '%Y-%m-%d %H:%M:%S.%f'), rewritten_intent: "Convert a DateTime string back to a DateTime object of format '%Y-%m-%d %H:%M:%S.%f'"
92
  ```
93
  # Training Hyperparameters
94
- Non-Default Hyperparameters:
95
- **per_device_train_batch_size:** 4
96
- **per_device_eval_batch_size:** 4
97
- **gradient_accumulation_steps:** 2 (effective batch size = 8)
98
- **num_train_epochs:** 10
99
- **learning_rate:** 1e-4
100
- **fp16:** True
101
 
 
35
  (lm_head): Linear(in_features=768, out_features=32100, bias=False)
36
  )
37
 
38
+ ```
39
+
40
  ```bash
41
  pip install -U transformers torch datasets
42
  #Then, load the model and run inference:
 
45
 
46
  # Download from the 🤗 Hub
47
  ```python
48
+ model_name = "AventIQ-AI/t5_code_summarizer" # Update with your HF model ID
49
  tokenizer = RobertaTokenizer.from_pretrained(model_name)
50
  model = T5ForConditionalGeneration.from_pretrained(model_name)
51
 
 
93
  snippet: datetime.strptime('2010-11-13 10:33:54.227806', '%Y-%m-%d %H:%M:%S.%f'), rewritten_intent: "Convert a DateTime string back to a DateTime object of format '%Y-%m-%d %H:%M:%S.%f'"
94
  ```
95
  # Training Hyperparameters
96
+ ### Non-Default Hyperparameters:
97
+ - **per_device_train_batch_size:** 4
98
+ - **per_device_eval_batch_size:** 4
99
+ - **gradient_accumulation_steps:** 2 (effective batch size = 8)
100
+ - **num_train_epochs:** 10
101
+ - **learning_rate:** 1e-4
102
+ - **fp16:** True
103