Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- lars1234/story_writing_benchmark
|
| 5 |
+
base_model:
|
| 6 |
+
- lars1234/Mistral-Small-24B-Instruct-2501-writer
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Mistral-Small-24B-Instruct-2501-writer-AWQ
|
| 10 |
+
|
| 11 |
+
This model is the 4-bit AWQ-quantized version of [Mistral-Small-24B-Instruct-2501-writer](lars1234/Mistral-Small-24B-Instruct-2501-writer).
|
| 12 |
+
|
| 13 |
+
- **Quantization Method**: AWQ (Activation-aware Weight Quantization)
|
| 14 |
+
- **Quantization Configuration**:
|
| 15 |
+
- Bit Width: 4-bit
|
| 16 |
+
- Group Size: 128
|
| 17 |
+
- Zero Point: Enabled
|
| 18 |
+
- Version: GEMM
|