Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Saba-Ethiopia
|
| 2 |
+
|
| 3 |
+
A fine-tuned LLaMA-3 4-bit model trained for [specific purpose].
|
| 4 |
+
|
| 5 |
+
## Model Details
|
| 6 |
+
- **Base Model**: LLaMA-3 3B
|
| 7 |
+
- **Quantization**: 4-bit
|
| 8 |
+
- **Use Case**: [Describe what the model is fine-tuned for]
|
| 9 |
+
|
| 10 |
+
## Usage
|
| 11 |
+
To use this model in your code:
|
| 12 |
+
```python
|
| 13 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 14 |
+
|
| 15 |
+
model = AutoModelForCausalLM.from_pretrained("modeltrainer1/Saba-Ethiopia", torch_dtype="auto")
|
| 16 |
+
tokenizer = AutoTokenizer.from_pretrained("modeltrainer1/Saba-Ethiopia")
|
| 17 |
+
|
| 18 |
+
inputs = tokenizer("Your input text here", return_tensors="pt")
|
| 19 |
+
outputs = model.generate(**inputs)
|
| 20 |
+
print(tokenizer.decode(outputs[0]))
|