Update README.md
Browse files
README.md
CHANGED
|
@@ -31,6 +31,16 @@ The following specifications:
|
|
| 31 |
- **Maximum Sequence Length (context):** 32,768 tokens
|
| 32 |
## Usage
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
### Initial
|
| 35 |
```python
|
| 36 |
|
|
|
|
| 31 |
- **Maximum Sequence Length (context):** 32,768 tokens
|
| 32 |
## Usage
|
| 33 |
|
| 34 |
+
| Model | Quantized | Size | Hardware Requirement |
|
| 35 |
+
|-------------|-----------|--------|--------------------------|
|
| 36 |
+
| APUS-xDAN4.0-MoE-0402.Q2_K.gguf | Q2_K | 39G | 2x24G GPU memory |
|
| 37 |
+
| APUS-xDAN4.0-MoE-0402.Q3_K_M_Matrix.gguf | Q3_K_M | 51G | 2x24G GPU memory |
|
| 38 |
+
| Large | No | Large | At least 8GB GPU memory |
|
| 39 |
+
| Quantized-S | Yes | Small | At least 1GB GPU memory |
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
|
| 44 |
### Initial
|
| 45 |
```python
|
| 46 |
|