Update README.md
#4
by
zicsx
- opened
README.md
CHANGED
@@ -421,9 +421,9 @@ To begin using Project Indus LLM for your projects, follow these steps to set up
|
|
421 |
# Load model directly
|
422 |
|
423 |
```python
|
424 |
-
from transformers import
|
425 |
|
426 |
-
model =
|
427 |
tokenizer = AutoTokenizer.from_pretrained("nickmalhotra/ProjectIndus")
|
428 |
|
429 |
# Example inference
|
@@ -454,3 +454,21 @@ output = model.generate(input_ids,
|
|
454 |
num_return_sequences=1,
|
455 |
)
|
456 |
print(tokenizer.decode(output[0], skip_special_tokens=False))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
421 |
# Load model directly
|
422 |
|
423 |
```python
|
424 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
425 |
|
426 |
+
model = AutoModelForCausalLM.from_pretrained("nickmalhotra/ProjectIndus")
|
427 |
tokenizer = AutoTokenizer.from_pretrained("nickmalhotra/ProjectIndus")
|
428 |
|
429 |
# Example inference
|
|
|
454 |
num_return_sequences=1,
|
455 |
)
|
456 |
print(tokenizer.decode(output[0], skip_special_tokens=False))
|
457 |
+
|
458 |
+
## Disclaimer
|
459 |
+
|
460 |
+
#### Model Limitations
|
461 |
+
|
462 |
+
Project Indus LLM is trained with single instruction tuning, which may result in hallucinations—instances where the model generates plausible but inaccurate information. Users should exercise caution, especially in scenarios requiring high factual accuracy.
|
463 |
+
|
464 |
+
#### Adaptation for Specific Use Cases
|
465 |
+
|
466 |
+
Project Indus LLM is designed as a foundational model suitable for further development and fine-tuning. Users are encouraged to adapt and refine the model to meet specific requirements of their applications.
|
467 |
+
|
468 |
+
#### Recommendations for Fine-Tuning
|
469 |
+
|
470 |
+
- **Identify Specific Needs**: Clearly define the requirements of your use case to guide the fine-tuning process.
|
471 |
+
- **Curate Targeted Data**: Ensure the training data is relevant and of high quality to improve model performance.
|
472 |
+
- **Continuous Evaluation**: Regularly assess the model's performance during and after fine-tuning to maintain accuracy and reduce biases.
|
473 |
+
|
474 |
+
This disclaimer aims to provide users with a clear understanding of the model's capabilities and limitations, facilitating its effective application and development.
|