Commit
•
ab5f4eb
1
Parent(s):
98df89f
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: xxx777xxxASD/L3.1-ClaudeMaid-4x8B
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
license: other
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
quantized_by: Reiterate3680
|
| 8 |
+
---
|
| 9 |
+
# Experimental fixed long context GGUFs. Requires [this release](https://github.com/Nexesenex/kobold.cpp/releases/tag/v1.71013_b3455%2B9) or newer of the KoboldCPP frankenfork
|
| 10 |
+
|
| 11 |
+
Original Model: https://huggingface.co/xxx777xxxASD/L3.1-ClaudeMaid-4x8B
|
| 12 |
+
|
| 13 |
+
made with https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script
|
| 14 |
+
|
| 15 |
+
Models Q2_K_L, Q4_K_L, Q5_K_L, Q6_K_L, are using Q_8 output tensors and token embeddings
|
| 16 |
+
|
| 17 |
+
using bartowski's imatrix dataset
|