Instructions to use modularStarEncoder/ModularStarEncoder-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use modularStarEncoder/ModularStarEncoder-finetuned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="modularStarEncoder/ModularStarEncoder-finetuned", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("modularStarEncoder/ModularStarEncoder-finetuned", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -44,7 +44,7 @@ instruction_natural_language = "Represent this code description for retrieving s
|
|
| 44 |
code_snippet = "your code to embed here"
|
| 45 |
|
| 46 |
#You should follow this pattern to embed a snippet of code or natural language queries
|
| 47 |
-
sentence = f"{tokenizer.sep_token}{instruction_code}{tokenizer.sep_token}{code_snippet
|
| 48 |
|
| 49 |
#Tokenizing your sentence
|
| 50 |
tokenized_sentence = tokenizer(sentence, return_tensors="pt",truncation=True, max_length=2048)
|
|
|
|
| 44 |
code_snippet = "your code to embed here"
|
| 45 |
|
| 46 |
#You should follow this pattern to embed a snippet of code or natural language queries
|
| 47 |
+
sentence = f"{tokenizer.sep_token}{instruction_code}{tokenizer.sep_token}{code_snippet}{tokenizer.cls_token}"
|
| 48 |
|
| 49 |
#Tokenizing your sentence
|
| 50 |
tokenized_sentence = tokenizer(sentence, return_tensors="pt",truncation=True, max_length=2048)
|