Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- anthracite-org/magnum-v3-34b
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- awq
|
| 7 |
+
- text-generation-inference
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
## Model Details
|
| 11 |
+
|
| 12 |
+
This is a AWQ GEMM quant of magnum-v3-34b: https://huggingface.co/anthracite-org/magnum-v3-34b
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
### Model Description
|
| 16 |
+
|
| 17 |
+
Model has been quantized on 6xRTX4090, here are quantization parameters:
|
| 18 |
+
|
| 19 |
+
"zero_point": True,
|
| 20 |
+
"q_group_size": 128,
|
| 21 |
+
"w_bit": 4,
|
| 22 |
+
"version": "GEMM"
|
| 23 |
+
|