Update metadata with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,6 +1,24 @@
|
|
| 1 |
---
|
| 2 |
quantized_by: bartowski
|
| 3 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
## Llamacpp imatrix Quantizations of MiniMax-M2-REAP-162B-A10B by cerebras
|
|
|
|
| 1 |
---
|
| 2 |
quantized_by: bartowski
|
| 3 |
pipeline_tag: text-generation
|
| 4 |
+
tags:
|
| 5 |
+
- glm
|
| 6 |
+
- MOE
|
| 7 |
+
- pruning
|
| 8 |
+
- compression
|
| 9 |
+
readme: 'https://huggingface.co/cerebras/MiniMax-M2-REAP-162B-A10B/main/README.md
|
| 10 |
+
|
| 11 |
+
'
|
| 12 |
+
name: cerebras/MiniMax-M2-REAP-162B-A10B
|
| 13 |
+
description: 'This model was obtained by uniformly pruning 30% of experts in MiniMax-M2
|
| 14 |
+
using the REAP method.
|
| 15 |
+
|
| 16 |
+
'
|
| 17 |
+
language:
|
| 18 |
+
- en
|
| 19 |
+
base_model: cerebras/MiniMax-M2-REAP-162B-A10B
|
| 20 |
+
license: other
|
| 21 |
+
base_model_relation: quantized
|
| 22 |
---
|
| 23 |
|
| 24 |
## Llamacpp imatrix Quantizations of MiniMax-M2-REAP-162B-A10B by cerebras
|