Update README.md
Browse files
README.md
CHANGED
|
@@ -65,8 +65,8 @@ This model was developed as a research prototype to explore personality-driven f
|
|
| 65 |
- **Quantization**: 4-bit (nf4) during training
|
| 66 |
- **Final Format**: Full precision merged model (FP16)
|
| 67 |
- **Parameters**: ~4B
|
| 68 |
-
- **Context Length**:
|
| 69 |
-
- **Vocabulary Size**:
|
| 70 |
|
| 71 |
### LoRA Configuration
|
| 72 |
```
|
|
|
|
| 65 |
- **Quantization**: 4-bit (nf4) during training
|
| 66 |
- **Final Format**: Full precision merged model (FP16)
|
| 67 |
- **Parameters**: ~4B
|
| 68 |
+
- **Context Length**: 128K tokens
|
| 69 |
+
- **Vocabulary Size**: 262K tokens
|
| 70 |
|
| 71 |
### LoRA Configuration
|
| 72 |
```
|