Instructions to use Chengran98/codethinker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Chengran98/codethinker with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Chengran98/codethinker")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Chengran98/codethinker") model = AutoModel.from_pretrained("Chengran98/codethinker") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -51,5 +51,11 @@ prompt = instruct_prompt+{user promt}
|
|
| 51 |
|
| 52 |
response = model.generate(prompt, sampling_params=sampling_params)
|
| 53 |
|
|
|
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
```
|
|
|
|
|
|
| 51 |
|
| 52 |
response = model.generate(prompt, sampling_params=sampling_params)
|
| 53 |
|
| 54 |
+
```
|
| 55 |
|
| 56 |
+
# Evaluation
|
| 57 |
+
The final solution provided in this version of CodeThinker is currently found under:
|
| 58 |
+
```
|
| 59 |
+
## Final Solution -> ### Solution Code -> ```python[solution]```
|
| 60 |
```
|
| 61 |
+
[TO DO]: An upcoming release will include improvements by wrapping the code solution within a specialized token (<solution>...</solution>) to enhance parsing capabilities.
|